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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    This neuron highlights numeric literal tokens (e.g. integers or floating-point constants) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    inea
    -0.07
     Mast
    -0.07
     Scandinavian
    -0.06
    ิก
    -0.06
     contingency
    -0.06
     allocation
    -0.06
     Zinc
    -0.06
    戏
    -0.06
     decks
    -0.06
     gut
    -0.06
    POSITIVE LOGITS
     ){↵
    0.07
     ‫
    0.07
     무엇
    0.06
     شهر
    0.06
    <"
    0.06
    ٫
    0.06
    _EX
    0.06
    .intValue
    0.06
    parseInt
    0.06
    =batch
    0.06
    Act Density 0.004%

    No Known Activations