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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing negation or the absence of something

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

    not because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.62
     @"/
    -0.60
    RenderAtEndOf
    -0.51
     GenerationType
    -0.47
    Autoritní
    -0.40
    /*
    -0.40
     scanf
    -0.39
     للمعارف
    -0.38
     مشين
    -0.38
    styleType
    -0.38
    POSITIVE LOGITS
    IVEREF
    0.50
    chieht
    0.48
     bukan
    0.47
    følgelig
    0.47
    alignSelf
    0.46
     pioggia
    0.45
    Bukan
    0.44
     not
    0.43
    anthene
    0.42
     kvä
    0.42
    Act Density 0.218%

    No Known Activations