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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     will
    -0.07
     전문
    -0.07
    調
    -0.07
    束
    -0.06
     vrij
    -0.06
     RadioButton
    -0.06
    wolf
    -0.06
    님
    -0.06
    кта
    -0.06
    866
    -0.06
    POSITIVE LOGITS
     قسمت
    0.07
    готов
    0.07
    amous
    0.07
     Photographer
    0.06
     parental
    0.06
    rál
    0.06
    expanded
    0.06
    entic
    0.06
     شخصية
    0.06
    上海
    0.06
    Act Density 0.049%

    No Known Activations