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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron fires on isolated validation‐rule keys (e.g. “accepted”, “email”, “alpha_dash”, etc.) in code files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    RITE
    -0.07
    ğinden
    -0.07
    jerne
    -0.06
    Goals
    -0.06
    응
    -0.06
    る
    -0.06
     ま
    -0.06
     açısından
    -0.06
     temples
    -0.06
    ิเศษ
    -0.06
    POSITIVE LOGITS
    .Complete
    0.07
     Washer
    0.06
    >{$
    0.06
    DidLoad
    0.06
     secluded
    0.06
     Allied
    0.06
    sl
    0.06
     Raise
    0.06
     Drinks
    0.06
     Partial
    0.06
    Act Density 0.003%

    No Known Activations