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

    Neuronpedia

    INDEX
    Explanations

    examples

    np_max-act · gemini-2.0-flash

    This neuron detects numeric values, especially decimal numbers and measurements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Fol
    -0.07
     usur
    -0.07
     tantal
    -0.07
    EVER
    -0.06
    REET
    -0.06
     ign
    -0.06
    شد
    -0.06
    _estimators
    -0.06
    	total
    -0.06
    desired
    -0.06
    POSITIVE LOGITS
    maps
    0.07
     широк
    0.06
     optimizing
    0.06
    "{
    0.06
     продуктов
    0.06
     گذاری
    0.06
    放
    0.06
    Lint
    0.06
    _COMPILER
    0.06
     uploaded
    0.06
    Act Density 0.179%

    No Known Activations