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

    Neuronpedia

    INDEX
    Explanations

    Pearl

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    摘编
    -0.07
    mtime
    -0.07
     auc
    -0.07
    ().__
    -0.07
    .Fatal
    -0.07
    Qu
    -0.07
     Ark
    -0.07
    int
    -0.06
    隨
    -0.06
    🛁
    -0.06
    POSITIVE LOGITS
    repair
    0.07
    นอน
    0.07
    experimental
    0.07
     kullan
    0.07
     Jewel
    0.07
     initialValue
    0.06
     enumerable
    0.06
    磋
    0.06
    Ϋ
    0.06
     callee
    0.06
    Act Density 0.009%

    No Known Activations