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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and access modifiers

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

    programming keywords: public, namespace, extern, template

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wikipagina
    -0.79
     تضيفلها
    -0.78
    ########.
    -0.73
     zoude
    -0.71
     erſt
    -0.69
     ProtoMessage
    -0.68
    NameInMap
    -0.68
     ddelwed
    -0.68
    exitRule
    -0.67
     ſind
    -0.66
    POSITIVE LOGITS
    uxxxx
    0.37
    illige
    0.30
     campagna
    0.30
     maler
    0.30
    ボー
    0.29
     she
    0.28
     ="";
    0.28
     Kammer
    0.28
    antMatchers
    0.28
     viol
    0.28
    Act Density 0.039%

    No Known Activations