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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron flags press‐release metadata—publisher or newswire identifiers (site names, domains) and dateline elements (city/state and source tags).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _provider
    -0.07
     bé
    -0.07
    production
    -0.07
    یلی
    -0.06
    MISSION
    -0.06
    لمه
    -0.06
     Rak
    -0.06
    exclude
    -0.06
    ,…↵↵
    -0.06
    рол
    -0.06
    POSITIVE LOGITS
    人民
    0.07
    �
    0.06
     cape
    0.06
     Když
    0.06
     жид
    0.06
    _lex
    0.06
    出来
    0.06
     Theresa
    0.06
    asics
    0.06
     futuristic
    0.06
    Act Density 0.003%

    No Known Activations