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

    Neuronpedia

    INDEX
    Explanations

    language and context related to color

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.57
    (
    0.52
     (
    0.47
    {-
    0.47
    安全
    0.46
     (“
    0.44
    h
    0.43
     (**
    0.43
     ως
    0.42
     de
    0.42
    POSITIVE LOGITS
     सुनेंरोक
    0.50
     இறந்த
    0.48
    ቱም
    0.47
    덬
    0.46
     hõ
    0.46
    ರ್ಗ
    0.45
     vermelho
    0.45
     tiktok
    0.45
     অতঃ
    0.44
     GoObject
    0.44
    Act Density 0.000%

    No Known Activations