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

    Neuronpedia

    INDEX
    Explanations

    variable names and function definitions within programming code

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

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ✭✭
    -0.49
    NewUrlParser
    -0.48
    IBOutlet
    -0.48
     EClass
    -0.48
     Burch
    -0.47
     Мексичка
    -0.47
    BeginContext
    -0.44
    moveToNext
    -0.43
    MetaType
    -0.42
     judged
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.42
    rician
    0.41
     canst
    0.37
    Sor
    0.35
    manda
    0.35
    icago
    0.34
     démo
    0.34
    swick
    0.34
    vician
    0.33
    sqm
    0.33
    Act Density 0.018%

    No Known Activations