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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

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

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    retched
    -0.07
     hookers
    -0.07
    传
    -0.06
    Theme
    -0.06
    epar
    -0.06
     cooled
    -0.06
    quiet
    -0.06
    غيل
    -0.06
    .watch
    -0.06
     Meg
    -0.06
    POSITIVE LOGITS
     novo
    0.07
     precinct
    0.07
    ザー
    0.07
     Produk
    0.06
     tấn
    0.06
     eventos
    0.06
    otate
    0.06
    érience
    0.06
     Actor
    0.06
    níků
    0.06
    Act Density 0.039%

    No Known Activations