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

    Neuronpedia

    INDEX
    Explanations

    non-english text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HasMaxLength
    -0.07
     Mang
    -0.07
     kabul
    -0.06
    ีก
    -0.06
     ह
    -0.06
    Stats
    -0.06
    erap
    -0.06
     plav
    -0.06
    Sing
    -0.06
     Increases
    -0.06
    POSITIVE LOGITS
    ??↵↵
    0.07
     wx
    0.07
    least
    0.07
    ))))↵↵
    0.07
    /free
    0.06
     провод
    0.06
    ativas
    0.06
    Cb
    0.06
    ，本
    0.06
     taille
    0.06
    Act Density 0.000%

    No Known Activations