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

    Neuronpedia

    INDEX
    Explanations

    cause damage or harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     criminality
    0.86
     malignancies
    0.80
     tumorigen
    0.76
    NaBr
    0.76
    দোষ
    0.73
     enerji
    0.71
     экстре
    0.71
    λογ
    0.70
    波动
    0.70
    অপ
    0.68
    POSITIVE LOGITS
    d
    0.80
     or
    0.80
    et
    0.77
    c
    0.77
    k
    0.75
    y
    0.73
    p
    0.71
    e
    0.70
     petals
    0.69
    b
    0.68
    Act Density 0.012%

    No Known Activations