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

    Neuronpedia

    INDEX
    Explanations

    closing curly braces in code syntax structures

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

    code structure and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -1.14
     <>",
    -0.86
     فريبيس
    -0.72
    цездатний
    -0.72
     يتيمه
    -0.71
     виправивши
    -0.68
    verwijspagina
    -0.65
     незавершена
    -0.65
    InitVars
    -0.63
    BeginContext
    -0.62
    POSITIVE LOGITS
     dikeluarkan
    0.33
     NgModule
    0.33
    дования
    0.32
    værende
    0.32
     ucapnya
    0.31
    这种情况
    0.31
     oluştur
    0.31
    ührung
    0.30
     menetap
    0.30
     sorpresas
    0.30
    Act Density 0.013%

    No Known Activations