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

    Neuronpedia

    INDEX
    Explanations

    French opera lyrics and related terms.

    oai_token-act-pair · gemini-2.0-flash

    multiple languages and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Majefty
    -1.04
     Eſ
    -0.98
     Efq
    -0.96
     ſeveral
    -0.89
     becauſe
    -0.89
     Monfieur
    -0.88
    ſelves
    -0.88
     myſelf
    -0.88
     ſtate
    -0.87
     whoſe
    -0.85
    POSITIVE LOGITS
    char
    0.52
    expandindo
    0.50
    
    0.45
     Rest
    0.43
    getSimpleName
    0.42
    انيف
    0.41
     char
    0.41
     [
    0.40
    BRACK
    0.40
     sub
    0.40
    Act Density 0.708%

    No Known Activations