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

    Neuronpedia

    INDEX
    Explanations

    code or technical contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     рис
    -0.06
     TRE
    -0.06
    .default
    -0.06
     Oprah
    -0.06
     вперед
    -0.06
    erge
    -0.06
     запах
    -0.06
     Effect
    -0.06
     chests
    -0.06
    _WARN
    -0.06
    POSITIVE LOGITS
     sigh
    0.07
    字符
    0.06
     keyboard
    0.06
    디
    0.06
     Sunrise
    0.06
    email
    0.06
     railways
    0.06
     Rooney
    0.06
     дат
    0.06
     Define
    0.06
    Act Density 0.000%

    No Known Activations