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

    Neuronpedia

    INDEX
    Explanations

    semicolon parentheses code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ektir
    -0.07
    Nonce
    -0.06
     khám
    -0.06
     prosperity
    -0.06
    (Yii
    -0.06
    clud
    -0.06
    Promise
    -0.06
     mouseClicked
    -0.06
    igth
    -0.06
     先
    -0.06
    POSITIVE LOGITS
    zan
    0.08
     lunar
    0.06
    ';↵↵↵↵
    0.06
     unpopular
    0.06
     quotations
    0.06
    ;<
    0.06
    =============
    0.06
    GOP
    0.06
    graph
    0.06
     tapi
    0.06
    Act Density 0.043%

    No Known Activations