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

    Neuronpedia

    INDEX
    Explanations

    hood

    np_max-act · gemini-2.0-flash

    This neuron spots discussions of internal implementation details, specifically the phrase “under the hood” or similar low-level commentary.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     καν
    -0.07
    _True
    -0.07
     polish
    -0.07
     حضور
    -0.07
     nhu
    -0.07
    ician
    -0.07
    mue
    -0.06
    かない
    -0.06
    (_:
    -0.06
    SJ
    -0.06
    POSITIVE LOGITS
     QHBoxLayout
    0.07
     göz
    0.06
    秘
    0.06
     Savaşı
    0.06
     cust
    0.06
    ATA
    0.06
    měr
    0.06
     куб
    0.05
    _wf
    0.05
     अग
    0.05
    Act Density 0.012%

    No Known Activations