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

    Neuronpedia

    INDEX
    Explanations

    phrases that clarify reasoning or explanations

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

    what that explains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.71
    setVerticalGroup
    -0.59
    Datuak
    -0.59
     IconData
    -0.57
    InputBorder
    -0.57
    IVEREF
    -0.53
    LookAnd
    -0.52
    djangoproject
    -0.52
    MLLoader
    -0.51
    Hentet
    -0.51
    POSITIVE LOGITS
    énéral
    0.29
    깥
    0.28
    惑
    0.28
    engage
    0.28
    новништво
    0.28
    fällig
    0.27
     вперед
    0.26
    PRNewswire
    0.26
    upassen
    0.25
    FO
    0.25
    Act Density 0.260%

    No Known Activations