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

    Neuronpedia

    INDEX
    Explanations

    double, float data types

    np_max-act · gemini-2.0-flash

    The neuron responds to floating‐point numeric literals (decimal numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     weit
    -0.09
    West
    -0.07
    部门
    -0.07
    ãi
    -0.07
     RedirectTo
    -0.07
    _Find
    -0.07
     Fare
    -0.07
    LOSE
    -0.06
    itto
    -0.06
    Wer
    -0.06
    POSITIVE LOGITS
    /screen
    0.07
     Tx
    0.07
     adoles
    0.06
     Signed
    0.06
     тр
    0.06
     nitrogen
    0.06
    /star
    0.06
    .Secret
    0.06
    .InputStream
    0.06
    rollable
    0.06
    Act Density 0.031%

    No Known Activations