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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens (digits and numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     opting
    -0.06
    .XtraGrid
    -0.06
     goTo
    -0.06
     산
    -0.06
    它
    -0.06
    .goBack
    -0.06
     千
    -0.06
    弃
    -0.06
     empire
    -0.06
    <k
    -0.06
    POSITIVE LOGITS
    _SAMPLES
    0.07
     wsz
    0.06
     Loved
    0.06
     Taco
    0.06
     محافظ
    0.06
     Jurassic
    0.06
     Chemistry
    0.06
    beautiful
    0.06
     tourists
    0.06
     Trigger
    0.06
    Act Density 0.007%

    No Known Activations