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

    Neuronpedia

    INDEX
    Explanations

    Fashion/news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (payload
    -0.08
    geme
    -0.08
     dàng
    -0.08
    ermit
    -0.08
    (mapped
    -0.08
    ýs
    -0.08
    .metro
    -0.07
    itia
    -0.07
     הרח
    -0.07
    لىقى
    -0.07
    POSITIVE LOGITS
     എന്നിവർ
    0.08
    ೇನೆ
    0.08
    ാർത്ഥ
    0.07
    _delete
    0.07
    ില്ല
    0.07
    ୋ
    0.07
    ിട്ടില്ല
    0.07
    ീവ
    0.07
    ാറ്റ
    0.07
    ಾರ್
    0.07
    Act Density 0.202%

    No Known Activations