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

    Neuronpedia

    INDEX
    Explanations

    since

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    捕
    -0.06
    ременно
    -0.06
     어머니
    -0.06
     Прав
    -0.06
     コ
    -0.06
    _DUMP
    -0.06
    .exp
    -0.06
    ाफ
    -0.06
     Các
    -0.06
     پدر
    -0.06
    POSITIVE LOGITS
    nine
    0.06
     rounding
    0.06
     cz
    0.06
    면적
    0.06
     powerful
    0.06
    YN
    0.06
    idine
    0.05
     firms
    0.05
     nomine
    0.05
    ěji
    0.05
    Act Density 0.012%

    No Known Activations