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

    Neuronpedia

    INDEX
    Explanations

    Asterisks and number signs

    np_max-act · gemini-2.0-flash

    The neuron detects the leading asterisk “*” markers used in block-comment license headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Riverside
    -0.07
    PLEMENT
    -0.06
     fame
    -0.06
    práv
    -0.06
     fandom
    -0.06
    _mac
    -0.06
    _ALPHA
    -0.06
     tgt
    -0.06
     shady
    -0.06
    .pag
    -0.06
    POSITIVE LOGITS
     triggering
    0.06
     Cyan
    0.06
    였다
    0.06
     Naturally
    0.06
    *******/↵↵
    0.06
     yük
    0.06
    若
    0.06
    odí
    0.06
    كه
    0.06
    ↵        
↵
    0.06
    Act Density 0.037%

    No Known Activations