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

    Neuronpedia

    INDEX
    Explanations

    many

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jue
    -0.07
    .Formatting
    -0.07
    شن
    -0.07
     Converter
    -0.07
    ุง
    -0.07
    وجب
    -0.07
     numa
    -0.07
     bụng
    -0.07
    =min
    -0.07
    ++);↵
    -0.06
    POSITIVE LOGITS
     aria
    0.07
     Mail
    0.07
     Finding
    0.07
     Eck
    0.07
     Elaine
    0.07
    _E
    0.07
    发扬
    0.07
    说明
    0.06
     za
    0.06
    叙述
    0.06
    Act Density 0.067%

    No Known Activations