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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens, particularly decimal numbers (floating‐point measurements) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    toolbox
    -0.07
    esta
    -0.06
    800
    -0.06
    @if
    -0.06
    847
    -0.06
    Roger
    -0.06
     Distribution
    -0.06
    grades
    -0.06
    777
    -0.06
     wird
    -0.06
    POSITIVE LOGITS
    主義
    0.07
    @testable
    0.07
     PRIMARY
    0.07
    .navCtrl
    0.06
    jspb
    0.06
     cre
    0.06
    (Unknown
    0.06
     初始化
    0.06
     {
↵
    0.06
     volupt
    0.06
    Act Density 0.145%

    No Known Activations