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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    The neuron fires on nonzero activations for words that signal formal rulings or approvals (e.g. “approved,” “accepted,” “rejected,” “decided”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    guna
    -0.06
    _scale
    -0.06
     Erdoğan
    -0.06
     cánh
    -0.06
    creds
    -0.06
     pancakes
    -0.06
     Drinks
    -0.06
     Jiří
    -0.06
     худож
    -0.06
     rodin
    -0.06
    POSITIVE LOGITS
     convention
    0.07
     GENERAL
    0.07
    》（
    0.06
     داخلی
    0.06
     department
    0.06
     labeled
    0.06
    .StylePriority
    0.06
     professional
    0.06
     usable
    0.06
    <IEnumerable
    0.06
    Act Density 0.025%

    No Known Activations