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

    Neuronpedia

    INDEX
    Explanations

    این

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TW
    -0.09
    �
    -0.08
     unt
    -0.08
     אה
    -0.07
     reciproc
    -0.07
    don
    -0.07
     ов
    -0.07
     nep
    -0.07
     secur
    -0.07
     appreci
    -0.07
    POSITIVE LOGITS
     Hayes
    0.08
    孔
    0.08
    .bootstrap
    0.07
    lc
    0.07
     Humans
    0.07
    Resid
    0.07
     Roch
    0.07
    منة
    0.07
     Hole
    0.07
    терес
    0.07
    Act Density 0.002%

    No Known Activations