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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WARD
    -0.08
    聯絡
    -0.07
    机电
    -0.07
    Soft
    -0.07
    佣金
    -0.07
     addChild
    -0.07
     clothing
    -0.07
     affirmative
    -0.07
     Feed
    -0.07
     urged
    -0.06
    POSITIVE LOGITS
    >d
    0.07
     pubs
    0.07
    ↱
    0.06
    (expr
    0.06
    (has
    0.06
     dbName
    0.06
    遭遇
    0.06
     wrapper
    0.06
    做完
    0.06
     sca
    0.06
    Act Density 0.002%

    No Known Activations