Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    elements that signify data structure or programming syntax, particularly in relation to function calls and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to context or arguments within a programming or technical setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Arab tribes, names, signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.72
    UserScript
    -0.69
     Signalez
    -0.69
    dafx
    -0.60
    SuccessListener
    -0.60
    tett
    -0.60
    PerformLayout
    -0.59
    Glej
    -0.59
    ::~
    -0.57
    InjectMocks
    -0.57
    POSITIVE LOGITS
     للاسماء
    0.70
     Dumnezeu
    0.58
     engraçadas
    0.54
     kasarigan
    0.54
     inocente
    0.51
     revient
    0.50
     citoy
    0.50
     assise
    0.50
     Pliny
    0.50
     cristiana
    0.49
    Act Density 0.009%

    No Known Activations