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

    Neuronpedia

    INDEX
    Explanations

    modelmodel or unittest.TestCase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (\
    1.11
    هِ
    0.92
    దని
    0.91
    (-
    0.91
    $('
    0.88
    __
    0.87
    hede
    0.87
    ্লীল
    0.87
     KeyError
    0.87
     የሆነ
    0.87
    POSITIVE LOGITS
    ों
    1.17
    ㅢ
    1.16
     chromatography
    1.08
    𝓹
    1.06
    itories
    1.06
     chores
    1.05
    s
    1.03
     фанта
    1.02
     خارج
    1.02
     تہ
    1.02
    Act Density 0.001%

    No Known Activations