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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash

    The neuron activates on numerals and decimal-style statistics, i.e. quantitative figures and performance metrics.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     několik
    -0.08
    "));↵
    -0.07
     Insert
    -0.06
     pressure
    -0.06
     garden
    -0.06
     needle
    -0.06
     GENERATED
    -0.06
     Liqu
    -0.06
    )]);↵
    -0.06
    imulation
    -0.06
    POSITIVE LOGITS
     Leadership
    0.07
    yses
    0.06
     vòng
    0.06
    /*@
    0.06
    학생
    0.06
    。\
    0.06
    smtp
    0.06
     وحدة
    0.06
    (points
    0.06
    斯
    0.06
    Act Density 0.013%

    No Known Activations