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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and elements related to programming or coding syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    bracket-like characters and specific code/technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیا
    -0.61
    IntoConstraints
    -0.60
    ckså
    -0.60
     الرياضيه
    -0.56
     Bolivar
    -0.54
     geweest
    -0.54
    ettür
    -0.53
    actéristi
    -0.51
    enumii
    -0.51
    bentar
    -0.50
    POSITIVE LOGITS
    《
    1.96
     《
    1.59
    ：《
    1.36
    ，《
    1.25
    、《
    1.17
    。《
    1.16
    　　《
    1.03
    .《
    1.01
    》《
    0.75
    〈
    0.73
    Act Density 0.001%

    No Known Activations