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

    Neuronpedia

    INDEX
    Explanations

    sights

    np_max-act · gemini-2.0-flash

    The neuron activates on words naming sensory experiences—sights, sounds, smells, etc.—i.e. descriptive sensory details.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    泉
    -0.08
     retiring
    -0.07
    .GetObject
    -0.07
     ánh
    -0.06
    _cd
    -0.06
    _open
    -0.06
    enburg
    -0.06
    تری
    -0.06
     biết
    -0.06
    lica
    -0.06
    POSITIVE LOGITS
    amam
    0.07
    imest
    0.07
    bakan
    0.07
    operative
    0.07
     مدیر
    0.06
     dafür
    0.06
    오
    0.06
    �
    0.06
    ارب
    0.06
     videog
    0.06
    Act Density 0.008%

    No Known Activations