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

    Neuronpedia

    INDEX
    Explanations

    most

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     massively
    -0.08
     betreff
    -0.08
    continued
    -0.08
    서를
    -0.07
     то
    -0.07
    -u
    -0.07
     überw
    -0.07
     №
    -0.07
     Sedan
    -0.07
    abad
    -0.07
    POSITIVE LOGITS
    तः
    0.10
     మంది
    0.10
     julọ
    0.10
    情况下
    0.10
     الأحيان
    0.10
    stay
    0.09
     대부분
    0.09
     लोग
    0.09
     ক্ষেত্রে
    0.08
     бывает
    0.08
    Act Density 0.045%

    No Known Activations