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

    Neuronpedia

    INDEX
    Explanations

    math/symbolic language

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—especially decimal numbers (floating-point literals)—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ۱۰
    -0.07
    -Oct
    -0.07
    amar
    -0.07
    Fun
    -0.07
    -d
    -0.06
    fo
    -0.06
     Dark
    -0.06
    BU
    -0.06
    #######↵
    -0.06
     清
    -0.06
    POSITIVE LOGITS
    RGB
    0.06
     zen
    0.06
     conven
    0.06
     piyas
    0.06
     là
    0.06
    uele
    0.06
    JSImport
    0.05
     gec
    0.05
     tük
    0.05
     erotica
    0.05
    Act Density 0.028%

    No Known Activations