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

    Neuronpedia

    INDEX
    Explanations

    edition

    np_max-act · gemini-2.0-flash

    This neuron responds to numbered list markers (e.g. “1.”, “1st edition”) and similar ordinal/numbered headings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     posting
    -0.07
     freshwater
    -0.06
     Behavioral
    -0.06
     Posting
    -0.06
    .getObject
    -0.06
     Goose
    -0.06
    iế
    -0.06
     sextreffen
    -0.06
    .header
    -0.06
    ывается
    -0.06
    POSITIVE LOGITS
     개인
    0.06
     mdb
    0.06
     Indie
    0.06
    anoi
    0.06
    _ctl
    0.06
    づ
    0.06
    _DIFF
    0.06
     Dek
    0.06
    ‎
    0.05
     сна
    0.05
    Act Density 0.110%

    No Known Activations