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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    行业内
    -0.07
    世界
    -0.07
    徘
    -0.07
    movement
    -0.07
    cause
    -0.07
    世界上
    -0.06
     async
    -0.06
     노
    -0.06
    aneous
    -0.06
    ไกล
    -0.06
    POSITIVE LOGITS
    ereço
    0.08
    Link
    0.07
    (:
    0.07
     chest
    0.07
    креп
    0.07
    (alias
    0.07
    صحف
    0.07
    听说过
    0.07
    _ref
    0.07
     ${({
    0.07
    Act Density 0.045%

    No Known Activations