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

    Neuronpedia

    INDEX
    Explanations

    small

    np_max-act · gemini-2.0-flash

    The neuron activates on floating-point numeric literals (decimal numbers) embedded in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    rijk
    -0.07
     fin
    -0.07
     víc
    -0.06
    .Ma
    -0.06
    -REAL
    -0.06
     можно
    -0.06
    iens
    -0.06
    BorderStyle
    -0.06
    IJ
    -0.06
    /xml
    -0.06
    POSITIVE LOGITS
     small
    0.07
     Кон
    0.07
     것이다
    0.07
    -small
    0.06
     stark
    0.06
     jong
    0.06
    _n
    0.06
     ARCH
    0.06
     highlighted
    0.06
     koji
    0.06
    Act Density 0.045%

    No Known Activations