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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    This neuron detects section‐header markers (e.g. “sec” and the following section number) in structured documents.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Path
    -0.07
    ruh
    -0.07
    CEL
    -0.06
     tuto
    -0.06
    itore
    -0.06
     perf
    -0.06
     altercation
    -0.06
     вор
    -0.06
    AFP
    -0.06
    dar
    -0.06
    POSITIVE LOGITS
    -Methods
    0.07
     kadın
    0.07
    -Headers
    0.07
    statements
    0.06
     campaign
    0.06
    AGING
    0.06
    _ARRAY
    0.06
    /lic
    0.06
     права
    0.06
     않은
    0.06
    Act Density 0.000%

    No Known Activations