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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CACHE
    -0.06
    ivation
    -0.06
    TemplateName
    -0.06
    _dll
    -0.06
    クリ
    -0.06
    lü
    -0.06
    relu
    -0.06
    _bn
    -0.06
    ро
    -0.06
     from
    -0.06
    POSITIVE LOGITS
    увалися
    0.07
     Family
    0.07
     pomocí
    0.07
    Specifier
    0.06
    Ut
    0.06
    .activ
    0.06
     deposit
    0.06
     automáticamente
    0.06
    cuador
    0.06
     toplum
    0.06
    Act Density 0.000%

    No Known Activations