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

    Neuronpedia

    INDEX
    Explanations

    financial data

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literals (especially decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    线
    -0.08
    現
    -0.07
     Razor
    -0.07
     　 　 　
    -0.06
    LOCATION
    -0.06
     ولی
    -0.06
    (sys
    -0.06
    .Itoa
    -0.06
    _EDEFAULT
    -0.06
    .DisplayMember
    -0.06
    POSITIVE LOGITS
     Wrestle
    0.07
    震
    0.07
     Covers
    0.07
     lots
    0.06
     방법
    0.06
     jap
    0.06
     substantive
    0.06
    _chance
    0.06
     ACPI
    0.06
     Killed
    0.06
    Act Density 0.036%

    No Known Activations