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

    Neuronpedia

    INDEX
    Explanations

    =============

    np_max-act · gemini-2.0-flash

    The neuron fires on the boilerplate comment blocks that open with “/*===…” and contain copyright/license headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    accepted
    -0.07
     WIDTH
    -0.06
    -c
    -0.06
    Communication
    -0.06
     camp
    -0.06
     Cameroon
    -0.06
    دهای
    -0.06
    Minimal
    -0.06
     dum
    -0.06
    _FIRE
    -0.06
    POSITIVE LOGITS
    ><
    0.06
     nrows
    0.06
    '><
    0.06
    clusive
    0.06
    ничес
    0.06
    	NullCheck
    0.06
     pageInfo
    0.06
    alis
    0.06
     crews
    0.06
    ======↵
    0.05
    Act Density 0.000%

    No Known Activations