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

    Neuronpedia

    INDEX
    Explanations

    format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etections
    -0.07
    FDA
    -0.07
     Kurds
    -0.07
    foon
    -0.06
     KUR
    -0.06
     besar
    -0.06
     موجود
    -0.06
    узы
    -0.06
     Garc
    -0.06
    лені
    -0.06
    POSITIVE LOGITS
    ,
↵
    0.06
    ）↵↵
    0.06
     [+
    0.06
    ``↵
    0.06
     specialists
    0.06
    "",↵
    0.06
    。</
    0.06
    @↵
    0.06
     Equals
    0.06
    らせ
    0.06
    Act Density 0.004%

    No Known Activations