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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Esc
    -0.06
     ж
    -0.06
    -delay
    -0.06
     centerX
    -0.06
    орд
    -0.06
     wings
    -0.06
     Männer
    -0.06
     width
    -0.06
     cols
    -0.05
    *width
    -0.05
    POSITIVE LOGITS
    RELEASE
    0.07
    _make
    0.07
     ');
↵
    0.07
    Interview
    0.06
    所属
    0.06
     kuruluş
    0.06
     numel
    0.06
    lili
    0.06
     Kata
    0.06
     quân
    0.06
    Act Density 0.088%

    No Known Activations