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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    The neuron fires on floating‐point numeric literals (decimal numbers with fractional parts) embedded in test error/log message strings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Otherwise
    -0.08
     weit
    -0.06
     plateau
    -0.06
     spear
    -0.06
    Portland
    -0.06
     май
    -0.06
    需要
    -0.06
     Finding
    -0.06
    rottle
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    ramids
    0.07
     Wrap
    0.07
     Sorting
    0.07
    ful
    0.06
     Resistance
    0.06
     приготовить
    0.06
    (itemView
    0.06
    .newInstance
    0.06
     Nutzung
    0.06
     gov
    0.06
    Act Density 0.002%

    No Known Activations