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

    Neuronpedia

    INDEX
    Explanations

    parallel

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on tokens representing decimal or floating-point numeric values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tween
    -0.07
     obtener
    -0.06
    Database
    -0.06
     Chess
    -0.06
    anian
    -0.06
     neglect
    -0.06
     esa
    -0.06
     peny
    -0.06
     参
    -0.06
    敷
    -0.06
    POSITIVE LOGITS
     parallel
    0.08
     treadmill
    0.07
    ')==
    0.07
     paralle
    0.07
    ار
    0.06
    TOT
    0.06
     مر
    0.06
     nost
    0.06
    USES
    0.06
    rays
    0.06
    Act Density 0.003%

    No Known Activations