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

    Neuronpedia

    INDEX
    Explanations

    `

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ాళ
    -0.08
     deri
    -0.08
     fashion
    -0.08
     diagno
    -0.08
     razvoja
    -0.08
    验
    -0.07
     trik
    -0.07
    কাৰ
    -0.07
    ಾಳಿ
    -0.07
     Einkauf
    -0.07
    POSITIVE LOGITS
     написал
    0.08
     привет
    0.08
    written
    0.08
     прекрасно
    0.08
    вуч
    0.07
    formatted
    0.07
    .chomp
    0.07
     Вам
    0.07
     humanitarian
    0.07
     reassurance
    0.07
    Act Density 0.015%

    No Known Activations