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

    Neuronpedia

    INDEX
    Explanations

    mall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _options
    -0.07
     öğretmen
    -0.07
     prodej
    -0.07
     Officer
    -0.07
     balık
    -0.07
     срав
    -0.06
    したら
    -0.06
     نزدیک
    -0.06
    _vp
    -0.06
    Object
    -0.06
    POSITIVE LOGITS
    olynomial
    0.07
    reas
    0.07
    @Slf
    0.06
     didnt
    0.06
    LATED
    0.06
    óln
    0.06
    .sam
    0.06
    OOSE
    0.06
    having
    0.06
     ----------------------------------------------------------------------------------------------------------------
    0.06
    Act Density 0.061%

    No Known Activations