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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash

    The neuron activates on numerical quantities—especially decimals, integers, and measurement values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Routes
    -0.07
     letras
    -0.06
    ichael
    -0.06
     شما
    -0.06
    mlink
    -0.06
    ^{
    -0.06
    Corn
    -0.06
    attachment
    -0.06
     reiterated
    -0.06
     именно
    -0.06
    POSITIVE LOGITS
    .Quit
    0.07
    /question
    0.06
    .oauth
    0.06
    _Core
    0.06
     Big
    0.06
    .CSS
    0.06
     Spice
    0.06
    づ
    0.06
    ativo
    0.06
    .quality
    0.06
    Act Density 0.038%

    No Known Activations