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

    Neuronpedia

    INDEX
    Explanations

    observation, seeing, first impressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dire
    -0.08
     xm
    -0.07
    Xm
    -0.07
     chapter
    -0.07
    -0.07
     chapters
    -0.07
    Something
    -0.07
    NER
    -0.07
     Happ
    -0.07
     ಕುರಿತು
    -0.07
    POSITIVE LOGITS
     glance
    0.15
    看来
    0.13
     unfamiliar
    0.12
     кажется
    0.12
     চোখ
    0.11
     નજર
    0.11
     superfic
    0.11
    眼
    0.11
     ظاهر
    0.10
     eyes
    0.10
    Act Density 0.024%
    No Known Activations