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

    Neuronpedia

    INDEX
    Explanations

    -induced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noises
    -0.08
    忺
    -0.08
     Alexandre
    -0.07
     rağ
    -0.07
    .push
    -0.07
    冁
    -0.07
     المس
    -0.07
     =[
    -0.07
    .logged
    -0.06
    Rated
    -0.06
    POSITIVE LOGITS
    �택
    0.08
    扼
    0.08
    ovic
    0.08
    IAM
    0.07
    aya
    0.07
    clin
    0.07
    اق
    0.07
    有机
    0.07
    neutral
    0.07
    bilit
    0.07
    Act Density 0.017%

    No Known Activations