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

    Neuronpedia

    INDEX
    Explanations

    online marketplace

    np_max-act · gemini-2.0-flash

    This neuron detects structured metadata fields—that is, table‐like label/value lines (with colons, numeric IDs, prices, dollar signs, buyer/seller tags, etc.) in documents.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     capita
    -0.07
    Choose
    -0.07
    aca
    -0.06
     ماده
    -0.06
     VIS
    -0.06
     Entre
    -0.06
     REM
    -0.06
     fourn
    -0.06
     AUD
    -0.06
    article
    -0.06
    POSITIVE LOGITS
    (xi
    0.07
     tako
    0.07
    _OP
    0.06
     obliged
    0.06
    redirectToRoute
    0.06
    .Nome
    0.06
     @{$
    0.06
    ("#{
    0.06
    ournemouth
    0.06
     Shorts
    0.06
    Act Density 0.202%

    No Known Activations