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

    Neuronpedia

    INDEX
    Explanations

    You

    np_max-act · gemini-2.0-flash

    This neuron highlights passages comparing or describing non-visual senses (e.g. sound, touch, heat) as analogies for vision.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     userInput
    -0.07
    _drawer
    -0.06
    Tk
    -0.06
     robbed
    -0.06
    มาร
    -0.06
    عداد
    -0.06
    '´
    -0.06
    ียร
    -0.06
    ',$
    -0.06
     gibi
    -0.06
    POSITIVE LOGITS
     xsi
    0.07
    ать
    0.07
     remote
    0.06
    accuracy
    0.06
    attach
    0.06
    (vec
    0.06
    єм
    0.06
    この
    0.06
     integrate
    0.06
    .Valid
    0.06
    Act Density 0.000%

    No Known Activations