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

    Neuronpedia

    INDEX
    Explanations

    From

    np_max-act · gemini-2.0-flash

    The neuron fires on the “Appeal From:” label line, specifically detecting the word “From” (and the following colon).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -selected
    -0.07
    ‌رس
    -0.07
    Positive
    -0.07
     reun
    -0.07
     ต
    -0.06
     Championship
    -0.06
    838
    -0.06
    "class
    -0.06
    白
    -0.06
    ري
    -0.06
    POSITIVE LOGITS
     UIColor
    0.07
    часно
    0.06
    .Margin
    0.06
    acoes
    0.06
     PAY
    0.06
     motive
    0.06
     COLL
    0.06
    oooooooo
    0.06
    ulfill
    0.06
    currentState
    0.06
    Act Density 0.001%

    No Known Activations