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

    Neuronpedia

    INDEX
    Explanations

    tasks and work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .basic
    -0.07
    orderBy
    -0.07
    alnum
    -0.06
     "\"
    -0.06
    phrase
    -0.06
    ЛО
    -0.06
     sperma
    -0.06
     ліка
    -0.06
    _SP
    -0.06
    _pars
    -0.06
    POSITIVE LOGITS
    [/
    0.06
     คณะ
    0.06
    óa
    0.06
     ราค
    0.06
     cafeteria
    0.06
     배우
    0.06
    уда
    0.06
    vature
    0.06
    Restaurant
    0.06
     پیشنه
    0.06
    Act Density 0.018%

    No Known Activations