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

    Neuronpedia

    INDEX
    Explanations

    descriptive writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    üks
    -0.08
     일반
    -0.08
    ಲ್ಲಿ
    -0.07
    landır
    -0.07
    -variable
    -0.07
    issons
    -0.07
     enables
    -0.07
     ermög
    -0.07
     جهت
    -0.07
     스마트
    -0.07
    POSITIVE LOGITS
    ，却
    0.09
     protagonist
    0.09
     strangely
    0.08
    少女
    0.08
     seaside
    0.08
     grud
    0.08
     विशाल
    0.08
     shimmering
    0.08
     तू
    0.08
    Doe
    0.08
    Act Density 0.075%

    No Known Activations