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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric expressions and measurements (digits, units, and numeric values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     potom
    -0.06
    .ur
    -0.06
    _bbox
    -0.06
    .Est
    -0.06
    /Grid
    -0.06
    Cooldown
    -0.06
    (typ
    -0.06
     flows
    -0.06
    _ret
    -0.06
    ρηση
    -0.06
    POSITIVE LOGITS
    436
    0.06
    noDB
    0.06
    -ли
    0.06
     insecure
    0.06
    кам
    0.06
    seys
    0.06
     ￥
    0.06
     classname
    0.06
     навк
    0.06
    .findall
    0.06
    Act Density 0.136%

    No Known Activations