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

    Neuronpedia

    INDEX
    Explanations

    Computer requests/jobs

    np_max-act · gemini-2.0-flash

    This neuron fires on words naming units of work or service tasks (e.g. “jobs,” “requests”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     wat
    -0.07
     costly
    -0.07
     sol
    -0.06
    elta
    -0.06
     ask
    -0.06
     Sun
    -0.06
    LIBINT
    -0.06
     перв
    -0.06
    Wed
    -0.06
    ئ
    -0.06
    POSITIVE LOGITS
    кість
    0.06
    ــــــــ
    0.06
     Cupertino
    0.06
    �
    0.06
     člověk
    0.06
     SCM
    0.06
    ">'.$
    0.06
     AIM
    0.06
     рів
    0.06
    custom
    0.06
    Act Density 0.029%

    No Known Activations