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

    Neuronpedia

    INDEX
    Explanations

    get

    np_max-act · gemini-2.0-flash

    This neuron fires on the names of functions (verbs like get, set, create, update, save) in code, i.e. tokens in function-definition headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     upp
    -0.07
    hibited
    -0.07
     aspiring
    -0.07
     yên
    -0.06
    ляться
    -0.06
     Kardash
    -0.06
     lf
    -0.06
     Patt
    -0.06
     vicious
    -0.06
    Bars
    -0.06
    POSITIVE LOGITS
     дал
    0.06
    KM
    0.06
     July
    0.06
    _mini
    0.06
     rin
    0.06
     AHL
    0.06
     aplicación
    0.06
     продукты
    0.06
     processo
    0.06
     Click
    0.06
    Act Density 0.040%

    No Known Activations