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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structure

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

    Code, math, and format strings

    np_acts-logits-general · gemini-2.0-flash

    programming and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.68
     الحره
    -0.56
     autorytatywna
    -0.56
    ----</
    -0.54
    новништво
    -0.49
    يكب
    -0.43
     للاسماء
    -0.43
    Datuak
    -0.42
    ScopeManager
    -0.41
    ellido
    -0.40
    POSITIVE LOGITS
    exitRule
    0.49
    ]--;
    0.47
    Становништво
    0.45
     illustratie
    0.42
     TAMBÉM
    0.42
     ilustracja
    0.41
     męska
    0.41
    CppCodeGen
    0.41
    uxxxx
    0.40
     Persönlichkeit
    0.40
    Act Density 0.951%

    No Known Activations