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

    Neuronpedia

    INDEX
    Explanations

    Russian characters and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     égard
    0.52
    😿
    0.51
     стаўкі
    0.51
     možda
    0.46
     Fallon
    0.45
     えっ
    0.45
     فونیټ
    0.45
     る
    0.44
     ImageIcon
    0.44
     सॉरी
    0.44
    POSITIVE LOGITS
    Д
    0.81
    С
    0.79
    За
    0.77
    Ро
    0.75
    При
    0.75
    Об
    0.75
    Р
    0.75
    У
    0.75
    В
    0.74
    На
    0.74
    Act Density 0.000%

    No Known Activations