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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kové
    -0.06
     CPI
    -0.06
    stered
    -0.06
    测
    -0.06
    :].
    -0.06
    нич
    -0.06
    uctose
    -0.06
    userid
    -0.06
    kas
    -0.05
     tích
    -0.05
    POSITIVE LOGITS
     mystery
    0.08
     documentation
    0.07
    ”。↵↵
    0.07
     CONVERT
    0.07
    _Per
    0.07
    .Ac
    0.07
     симптом
    0.07
     enabled
    0.07
     hete
    0.07
    \xff
    0.07
    Act Density 0.010%

    No Known Activations