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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens with decimal points (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     구글상위
    -0.07
     мик
    -0.07
    版
    -0.07
     생활
    -0.07
     bulk
    -0.06
     thích
    -0.06
    Positive
    -0.06
    :border
    -0.06
    구글상위
    -0.06
     pursuits
    -0.06
    POSITIVE LOGITS
     ด
    0.07
     \/
    0.07
     MSI
    0.06
     buddy
    0.06
     vznik
    0.06
    Analy
    0.06
     ".");↵
    0.06
     Ln
    0.06
     Elizabeth
    0.06
    equ
    0.06
    Act Density 0.007%

    No Known Activations