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

    Neuronpedia

    INDEX
    Explanations

    programming and mathematics

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens representing floating‐point numbers (decimal numerals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Proxy
    -0.06
     grid
    -0.06
    _Group
    -0.06
     insurance
    -0.06
    Anonymous
    -0.06
    gold
    -0.06
     initialization
    -0.05
    uctions
    -0.05
    Cookie
    -0.05
     australia
    -0.05
    POSITIVE LOGITS
    (files
    0.07
     křes
    0.07
     exacerb
    0.07
    (dto
    0.07
     ки
    0.06
    čel
    0.06
     axios
    0.06
     квітня
    0.06
    .selected
    0.06
    lisi
    0.06
    Act Density 0.788%

    No Known Activations