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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вопрос
    -0.07
    前的
    -0.06
    ependency
    -0.06
     homosex
    -0.06
     skeptic
    -0.06
    zą
    -0.06
    الع
    -0.06
     vej
    -0.06
    成為
    -0.06
     Gender
    -0.06
    POSITIVE LOGITS
    /main
    0.07
    (mat
    0.07
     "...
    0.06
     JE
    0.06
    FillColor
    0.06
     сколько
    0.06
    icine
    0.06
     날
    0.06
     imageNamed
    0.06
     ﾉ
    0.06
    Act Density 0.000%

    No Known Activations