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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    The neuron is looking for those special metadata/control tokens (e.g., header markers like <|start_header_id|>, <|end_header_id|>, and similar system‐formatting tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (INVOKE
    -0.07
    utr
    -0.07
     Allies
    -0.06
    unteers
    -0.06
    ibar
    -0.06
    delegate
    -0.06
    uable
    -0.06
    縮
    -0.06
     referrals
    -0.06
    acific
    -0.06
    POSITIVE LOGITS
    _inp
    0.07
    “.
    0.06
     anos
    0.06
    	pop
    0.06
     wore
    0.06
     nodes
    0.06
     przez
    0.06
    [loc
    0.06
     Budapest
    0.06
    (point
    0.06
    Act Density 0.070%

    No Known Activations