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

    Neuronpedia

    INDEX
    Explanations

    functions and structures related to programming syntax

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

    code constructs including imports and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.80
     виправивши
    -0.72
     arşivlendi
    -0.72
    +#+
    -0.72
    featureID
    -0.71
    Autoritní
    -0.71
    CloseOperation
    -0.69
    RTLR
    -0.69
    WebVitals
    -0.68
    NameInMap
    -0.67
    POSITIVE LOGITS
     Alters
    0.35
     global
    0.33
     passagers
    0.32
     samman
    0.31
    ramiento
    0.30
     globally
    0.30
     Johann
    0.30
     samlet
    0.30
     ar
    0.30
     GLOBAL
    0.29
    Act Density 0.009%

    No Known Activations