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

    Neuronpedia

    INDEX
    Explanations

    outcomes

    np_max-act · gemini-2.0-flash

    This neuron activates on numerical tokens representing decimal fractions (e.g., probabilities) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    римін
    -0.06
     authors
    -0.06
    /text
    -0.06
    fig
    -0.06
    ertype
    -0.06
     trot
    -0.06
     toilets
    -0.06
    interrupt
    -0.06
    _md
    -0.06
    ιά
    -0.06
    POSITIVE LOGITS
     раніше
    0.07
     dün
    0.07
    蘇
    0.07
     stove
    0.06
     Comparison
    0.06
    _cu
    0.06
     therm
    0.06
    requ
    0.06
    넷
    0.06
    0.06
    Act Density 0.008%

    No Known Activations