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

    Neuronpedia

    INDEX
    Explanations

    as or like

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens that include decimal points (i.e., fractional numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     threaded
    -0.07
     میزان
    -0.07
     سازمان
    -0.07
     Flem
    -0.07
     richness
    -0.07
     Florida
    -0.06
    _rule
    -0.06
     VP
    -0.06
     intersections
    -0.06
     cores
    -0.06
    POSITIVE LOGITS
     yönetic
    0.07
     abide
    0.07
    .IsEnabled
    0.06
    ient
    0.06
    Добав
    0.06
     irgend
    0.06
    …)↵↵
    0.06
    OutOfRange
    0.06
    iii
    0.06
    .")↵
    0.06
    Act Density 0.081%

    No Known Activations