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

    Neuronpedia

    INDEX
    Explanations

    time calculations

    np_max-act · gemini-2.0-flash

    The neuron activates on the fractional‐part tokens of decimal numbers (the bits after the decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     volupt
    -0.07
    ckpt
    -0.07
     půl
    -0.07
     reach
    -0.07
     california
    -0.06
    _dur
    -0.06
     λι
    -0.06
     folds
    -0.06
     недели
    -0.06
     Surveillance
    -0.06
    POSITIVE LOGITS
    keyCode
    0.06
     Hitler
    0.06
    uat
    0.06
    -wow
    0.06
    innerHTML
    0.06
    Sept
    0.06
     tinh
    0.06
     tournaments
    0.06
    <IActionResult
    0.06
    Right
    0.06
    Act Density 0.002%

    No Known Activations