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

    Neuronpedia

    INDEX
    Explanations

    Statistics

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric literal tokens—especially floating-point numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     distributors
    -0.07
    ias
    -0.06
     contempl
    -0.06
    <Address
    -0.06
     بانک
    -0.06
    (module
    -0.06
     Banana
    -0.06
    imizin
    -0.05
    -К
    -0.05
     isolate
    -0.05
    POSITIVE LOGITS
     dư
    0.07
     laat
    0.07
     plage
    0.07
    jets
    0.07
    asje
    0.07
     lawy
    0.07
     cél
    0.07
    巡
    0.07
    _SC
    0.07
    .ge
    0.06
    Act Density 0.033%

    No Known Activations