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

    Neuronpedia

    INDEX
    Explanations

    ()>

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literals—especially floating-point numbers—in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    TabPage
    -0.06
     ontology
    -0.06
    بینی
    -0.06
     Psychological
    -0.06
     цей
    -0.06
    стр
    -0.06
    427
    -0.06
    orgetown
    -0.06
    observ
    -0.06
    .Experimental
    -0.06
    POSITIVE LOGITS
     lah
    0.07
    $time
    0.07
    turn
    0.06
    witch
    0.06
    along
    0.06
    ilateral
    0.06
    ices
    0.06
    xies
    0.06
     аж
    0.06
     {.
    0.06
    Act Density 0.002%

    No Known Activations