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

    Neuronpedia

    INDEX
    Explanations

    anchors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蜂
    -0.08
     Cv
    -0.07
    吃饭
    -0.07
    赋
    -0.07
     responds
    -0.07
    .Att
    -0.07
    率领
    -0.07
    Hung
    -0.07
    :title
    -0.07
    都能
    -0.07
    POSITIVE LOGITS
    onitor
    0.07
    egrator
    0.07
    LineEdit
    0.07
     Erotic
    0.07
    ยะ
    0.07
     Variation
    0.07
    bundles
    0.06
    AJOR
    0.06
    鳉
    0.06
    ய
    0.06
    Act Density 0.003%

    No Known Activations