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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oldukları
    -0.06
    SUMER
    -0.06
    ITH
    -0.06
     barring
    -0.06
     Pressure
    -0.06
    INARY
    -0.06
    лением
    -0.06
     Hands
    -0.06
     SV
    -0.06
    962
    -0.06
    POSITIVE LOGITS
    ิจ
    0.07
    �
    0.06
    -names
    0.06
    茂
    0.06
    ___↵↵
    0.06
     outliers
    0.06
    оратив
    0.06
    @g
    0.06
     skies
    0.06
    (tok
    0.06
    Act Density 0.027%

    No Known Activations