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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is find explicit numeric quantities and measurements (e.g., numbers with units) in text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Resort
    -0.07
     Ensemble
    -0.06
    ेर
    -0.06
     speakers
    -0.06
     lbl
    -0.06
     cach
    -0.06
     Encoder
    -0.06
     Cindy
    -0.06
    me
    -0.06
     Worm
    -0.06
    POSITIVE LOGITS
    -Javadoc
    0.07
     उप
    0.07
    ิก
    0.07
     hiệu
    0.06
    μορ
    0.06
    .BL
    0.06
    .Loader
    0.06
     cevap
    0.06
    دهم
    0.06
    ohana
    0.06
    Act Density 0.343%

    No Known Activations