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

    Neuronpedia

    INDEX
    Explanations

    blocks of code or procedural structures in programming languages

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

    programming, foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.59
    UnusedPrivate
    -0.49
    DebuggerNonUser
    -0.45
    rogenic
    -0.42
    imread
    -0.41
    حياته
    -0.41
    usercontent
    -0.39
     Jeffer
    -0.39
    IllegalArgument
    -0.39
    marvin
    -0.39
    POSITIVE LOGITS
    msgTypes
    0.58
    Autoritní
    0.50
    endpush
    0.46
    migrationBuilder
    0.45
    astéro
    0.45
    :✨
    0.43
     stør
    0.42
     vœ
    0.42
     tilf
    0.42
     fometimes
    0.40
    Act Density 0.014%

    No Known Activations