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

    Neuronpedia

    INDEX
    Explanations

    angle brackets, parentheses, and words found in code.

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oare
    -0.48
    vill
    -0.45
    ť
    -0.44
    ora
    -0.43
    odi
    -0.42
    wer
    -0.42
    wad
    -0.41
    odes
    -0.41
    aly
    -0.40
    hurst
    -0.40
    POSITIVE LOGITS
     فريبيس
    0.91
    bootstrapcdn
    0.88
     صوتيه
    0.87
    HasForeignKey
    0.84
    
    0.82
     beginnetje
    0.81
    +#+#
    0.76
     disambiguazione
    0.76
    TableAdapter
    0.76
     ویکی‌پدی
    0.76
    Act Density 6.369%

    No Known Activations