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

    Neuronpedia

    INDEX
    Explanations

    function and method calls in code snippets

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

    decoding writing repeated data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.42
    GEBURTS
    -0.37
    FunctionFlags
    -0.37
    AnimationsModule
    -0.37
     indígen
    -0.37
     للاسماء
    -0.35
    WithMany
    -0.35
     onely
    -0.35
    CONCURRENT
    -0.35
    OCCURRED
    -0.34
    POSITIVE LOGITS
     empathi
    0.51
     signal
    0.51
     discreet
    0.49
     skip
    0.48
    migrationBuilder
    0.48
     sympathi
    0.47
     paraphrase
    0.47
    ፩
    0.47
    תם
    0.47
    rista
    0.46
    Act Density 0.066%

    No Known Activations