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

    Neuronpedia

    INDEX
    Explanations

    excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Кор
    -0.08
    닉
    -0.07
     samp
    -0.07
    .Comm
    -0.07
     �
    -0.07
     тв
    -0.07
    (";
    -0.07
     μόνο
    -0.06
    เฟ
    -0.06
     اسپ
    -0.06
    POSITIVE LOGITS
     fuel
    0.07
     jur
    0.06
    filename
    0.06
    ثير
    0.06
    ise
    0.06
    ограф
    0.06
     het
    0.06
     ESPN
    0.06
    اجع
    0.06
     guar
    0.05
    Act Density 0.000%

    No Known Activations