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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms that indicate data structures, methods, or function calls

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

    code statements ending with semicolon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.75
    ScopeManager
    -0.71
    Diweddarwch
    -0.68
    verwijspagina
    -0.67
    __(/*!
    -0.65
     الرياضيه
    -0.64
    tonsoft
    -0.62
    -),
    -0.61
    таратура
    -0.61
     $_(
    -0.60
    POSITIVE LOGITS
    ↵↵
    0.57
    ↵↵↵
    0.49
    ↵↵↵↵
    0.43
    ;
    0.40
    ↵↵↵↵↵↵
    0.36
    .
    0.34
    ↵
    0.34
    ↵↵↵↵↵↵↵
    0.34
     saken
    0.32
     final
    0.32
    Act Density 0.008%

    No Known Activations