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

    Neuronpedia

    INDEX
    Explanations

    strategy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Liber
    -0.07
     victim
    -0.07
     pokud
    -0.07
    victim
    -0.07
    rir
    -0.07
    UFFIX
    -0.06
     transporte
    -0.06
    piece
    -0.06
     <!--
    -0.06
     tie
    -0.06
    POSITIVE LOGITS
    ETwitter
    0.09
     YY
    0.07
    甲
    0.07
     Mov
    0.07
     til
    0.07
     ю
    0.06
     Fac
    0.06
     гра
    0.06
    轉
    0.06
     кв
    0.06
    Act Density 0.022%

    No Known Activations