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

    Neuronpedia

    INDEX
    Explanations

    characters

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect numeric tokens (numbers and numerical counts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .recipe
    -0.07
     loro
    -0.07
    チェ
    -0.07
    Ze
    -0.07
    owan
    -0.07
    ■
    -0.06
    олее
    -0.06
     Versions
    -0.06
     địch
    -0.06
    HIGH
    -0.06
    POSITIVE LOGITS
    _TAG
    0.06
    toDouble
    0.06
    shader
    0.06
    heets
    0.06
    $scope
    0.05
    	column
    0.05
    .toDouble
    0.05
    numeric
    0.05
     शब
    0.05
    :end
    0.05
    Act Density 0.004%

    No Known Activations