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

    Neuronpedia

    INDEX
    Explanations

    mutagenicity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cast
    -0.06
    _MAY
    -0.06
    KR
    -0.06
    _traits
    -0.05
    YN
    -0.05
    #######
    -0.05
    製
    -0.05
    ngx
    -0.05
    inee
    -0.05
     IICIII
    -0.05
    POSITIVE LOGITS
     Steve
    0.08
    akening
    0.07
    avan
    0.07
    aca
    0.07
     SendMessage
    0.07
     addict
    0.07
     Passage
    0.07
     Coupon
    0.07
    uttle
    0.07
     feeling
    0.07
    Act Density 0.002%

    No Known Activations