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

    Neuronpedia

    INDEX
    Explanations

    descriptor

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “descriptor” or “fd” (file-descriptor) identifiers and related constants.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    @NoArgsConstructor
    -0.07
     Jefferson
    -0.07
     Packet
    -0.07
    OMB
    -0.07
    berg
    -0.07
    Logger
    -0.06
     School
    -0.06
     chained
    -0.06
     patrol
    -0.06
    ió
    -0.06
    POSITIVE LOGITS
    [/
    0.06
     ενώ
    0.06
    u
    0.06
     противоп
    0.06
    鹿
    0.06
     ⓘ
    0.06
     olmadan
    0.05
    eph
    0.05
    olución
    0.05
    nu
    0.05
    Act Density 0.016%

    No Known Activations