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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     미
    -0.07
    番
    -0.06
     巴
    -0.06
     خانم
    -0.06
     mex
    -0.06
    enery
    -0.06
     Capitol
    -0.06
     препара
    -0.06
     Мор
    -0.06
    .pic
    -0.06
    POSITIVE LOGITS
    skill
    0.08
    ovaných
    0.07
     ά
    0.07
     abusing
    0.07
    ğını
    0.06
    √
    0.06
    (...)↵
    0.06
    AMA
    0.06
    ovaná
    0.06
    excluding
    0.06
    Act Density 0.000%

    No Known Activations