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

    Neuronpedia

    INDEX
    Explanations

    country

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    彻
    -0.07
    Раз
    -0.07
    _defs
    -0.06
    ichen
    -0.06
     safer
    -0.06
    pine
    -0.06
    /sec
    -0.06
     Pace
    -0.06
     оч
    -0.06
    !");
    -0.06
    POSITIVE LOGITS
     exempt
    0.07
    看到
    0.07
     citas
    0.07
     선거
    0.07
    ——
    0.07
     [|
    0.06
     Marxist
    0.06
    лев
    0.06
    小说
    0.06
    updates
    0.06
    Act Density 0.009%

    No Known Activations