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

    Neuronpedia

    INDEX
    Explanations

    patterns in numerical or metadata representations

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

    special delimiters and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.71
    awaiter
    -0.71
    oredCriteria
    -0.71
    adaptiveStyles
    -0.68
    parsedMessage
    -0.68
     ब्रेकडाउन
    -0.68
     فريبيس
    -0.68
     المعيارى
    -0.66
    OGND
    -0.65
    StructEnd
    -0.65
    POSITIVE LOGITS
    ner
    0.42
    wer
    0.40
     guys
    0.39
    nen
    0.38
    ler
    0.38
    zer
    0.38
     Wer
    0.37
    ing
    0.36
    ↵
    0.36
     
    0.36
    Act Density 0.018%

    No Known Activations