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

    Neuronpedia

    INDEX
    Explanations

    Scientific Notation

    np_max-act · gemini-2.0-flash

    tokens representing numbers, numeric measurements, or numeric/decimal expressions.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     undergrad
    -0.07
     marble
    -0.06
    opup
    -0.06
     tomb
    -0.06
     فیلم
    -0.06
     along
    -0.06
     invers
    -0.06
     Fans
    -0.06
     hoops
    -0.06
    burse
    -0.06
    POSITIVE LOGITS
    #a
    0.07
     ت
    0.07
    acute
    0.06
    _peak
    0.06
    Manifest
    0.06
    σμο
    0.06
    (ActionEvent
    0.06
     cumshot
    0.06
    lis
    0.06
    subtype
    0.06
    Act Density 0.055%

    No Known Activations