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

    Neuronpedia

    INDEX
    Explanations

    portion/sections

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric measurements or decimal values in technical descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    世紀
    -0.07
    &&
    -0.07
    Suc
    -0.07
     Faker
    -0.07
     براى
    -0.06
    :=
    -0.06
     whose
    -0.06
    :::::::::::::
    -0.06
    .now
    -0.06
    (xx
    -0.06
    POSITIVE LOGITS
     Fellow
    0.06
     вари
    0.06
     trait
    0.06
    (metrics
    0.06
     下载
    0.06
    bounding
    0.06
    _chip
    0.06
    ffmpeg
    0.06
    руп
    0.06
     witch
    0.06
    Act Density 0.033%

    No Known Activations