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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clearTimeout
    -0.07
     tuyến
    -0.06
     ☆
    -0.06
     철
    -0.06
    коз
    -0.06
    235
    -0.06
    453
    -0.06
     Tutorial
    -0.06
    신청
    -0.06
    动生成
    -0.06
    POSITIVE LOGITS
    يلي
    0.07
     conquered
    0.07
    ovu
    0.06
    _validation
    0.06
    ERGE
    0.06
    uner
    0.06
     Vul
    0.06
    enus
    0.06
    =",
    0.06
     outnumber
    0.06
    Act Density 0.275%

    No Known Activations