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

    Neuronpedia

    INDEX
    Explanations

    Standard output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OTAL
    -0.08
    .EventType
    -0.08
    ❄
    -0.07
     максимально
    -0.07
    動作
    -0.07
    /mark
    -0.07
    貘
    -0.07
     visually
    -0.07
    就餐
    -0.07
     Hund
    -0.06
    POSITIVE LOGITS
    ostream
    0.07
     openid
    0.07
     imposition
    0.07
     impass
    0.07
    (server
    0.07
    regions
    0.07
     lemma
    0.07
     deceive
    0.07
    失误
    0.06
    _capture
    0.06
    Act Density 0.003%

    No Known Activations