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

    Neuronpedia

    INDEX
    Explanations

    alternatives or conditions

    np_max-act · gemini-2.0-flash

    The neuron detects numeric tokens containing decimal points (i.e. floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     intest
    -0.06
     futile
    -0.06
    atik
    -0.06
     Magnet
    -0.06
     Kemp
    -0.06
     imaginative
    -0.06
     politicians
    -0.06
     kf
    -0.06
     Chad
    -0.06
    сен
    -0.06
    POSITIVE LOGITS
    MODULE
    0.07
    (nn
    0.07
    ΙΛ
    0.07
     самой
    0.07
     PT
    0.07
    navbar
    0.06
    鐵
    0.06
    LEX
    0.06
    ('</
    0.06
    编辑
    0.06
    Act Density 0.025%

    No Known Activations