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

    Neuronpedia

    INDEX
    Explanations

    Request

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on CamelCase identifiers defining request/response message types (e.g. GetModulesRequest, GetVersionsResponse) in protobuf service definitions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _logout
    -0.07
    night
    -0.07
     garn
    -0.07
    _tgt
    -0.06
     disemb
    -0.06
    gest
    -0.06
    Unauthorized
    -0.06
    stab
    -0.06
    ومات
    -0.06
     Zoom
    -0.06
    POSITIVE LOGITS
    izza
    0.07
     наличи
    0.07
     Rahman
    0.07
     larger
    0.06
     سخت
    0.06
     coli
    0.06
    ickness
    0.06
    ASA
    0.06
     neatly
    0.06
     gorgeous
    0.06
    Act Density 0.007%

    No Known Activations