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

    Neuronpedia

    INDEX
    Explanations

    Expiration dates

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens (digits and numbers) such as version numbers, dates, and other numeric sequences.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Clr
    -0.07
    icester
    -0.06
    TypeDef
    -0.06
    ERIC
    -0.06
    OUNTER
    -0.06
    CGColor
    -0.06
     counted
    -0.06
     SharedModule
    -0.06
     grades
    -0.06
    ACEMENT
    -0.06
    POSITIVE LOGITS
    审核
    0.07
    ์ซ
    0.07
     marin
    0.07
    填
    0.07
    黎
    0.07
     непосред
    0.06
    _COMPLETE
    0.06
     spear
    0.06
    _items
    0.06
     limitations
    0.06
    Act Density 0.008%

    No Known Activations