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

    Neuronpedia

    INDEX
    Explanations

    websites

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اند
    -0.07
     след
    -0.07
    49
    -0.07
    _ratings
    -0.07
    ียม
    -0.07
     thì
    -0.07
    情報
    -0.07
    mail
    -0.06
     EVERY
    -0.06
    δος
    -0.06
    POSITIVE LOGITS
    ilver
    0.07
    .scalar
    0.06
     \`
    0.06
     кім
    0.06
     yönetimi
    0.06
     Applications
    0.06
    (Runtime
    0.06
    .BorderStyle
    0.06
     bogus
    0.06
    ників
    0.06
    Act Density 0.031%

    No Known Activations