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

    Neuronpedia

    INDEX
    Explanations

    output

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on JavaScript object‐literal property names and identifiers (e.g. “module.exports,” “entry,” “output,” “plugins,” “devtool,” etc.) in config files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ImmutableList
    -0.06
    mapper
    -0.06
    .JPG
    -0.06
    arl
    -0.06
    .station
    -0.06
     бо
    -0.06
     "))↵
    -0.06
    (TypeError
    -0.06
    وران
    -0.06
    iel
    -0.06
    POSITIVE LOGITS
     Schneider
    0.07
    推
    0.07
    	buffer
    0.07
     Narrative
    0.07
     narrative
    0.06
     res
    0.06
    INVALID
    0.06
     SCE
    0.06
     přisp
    0.06
     writeTo
    0.06
    Act Density 0.001%

    No Known Activations