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

    Neuronpedia

    INDEX
    Explanations

    Product descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prowadzić
    -0.07
     Using
    -0.07
    耶�
    -0.07
     Każdy
    -0.07
    ṟ
    -0.07
     الإلكترو
    -0.07
     Nz
    -0.07
     التونسي
    -0.07
     tượng
    -0.06
     Penny
    -0.06
    POSITIVE LOGITS
    _DAMAGE
    0.08
    好久
    0.08
    .options
    0.07
    GEN
    0.07
    loat
    0.07
    _FOLDER
    0.07
    改革
    0.07
    的有效
    0.07
     "[
    0.07
    ❇
    0.07
    Act Density 0.019%

    No Known Activations