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

    Neuronpedia

    INDEX
    Explanations

    references to UI controls and elements within programming contexts

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

    Controls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.69
     ErrIntOverflow
    -0.57
    ſelf
    -0.55
    extAlignment
    -0.53
     myſelf
    -0.52
     poffible
    -0.50
     yyr
    -0.50
     ſche
    -0.50
     informée
    -0.50
     ftate
    -0.49
    POSITIVE LOGITS
    Controls
    3.41
     Controls
    2.22
    controls
    2.06
     controls
    1.91
     CONTROLS
    1.90
     controles
    1.33
     controla
    1.06
     controlling
    1.02
    Control
    1.00
     control
    0.98
    Act Density 0.001%

    No Known Activations