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

    Neuronpedia

    INDEX
    Explanations

    numbers, specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সবসময়
    0.33
     সবসময়
    0.32
     항상
    0.32
     देखील
    0.30
     доступ
    0.30
    各种
    0.29
     కూడా
    0.29
     доступны
    0.29
    ங்கும்
    0.29
    节日
    0.29
    POSITIVE LOGITS
     killed
    0.29
     iar
    0.29
    ’
    0.29
     nuova
    0.28
    '
    0.28
     nhưng
    0.28
     BUT
    0.28
     revenge
    0.27
     sodium
    0.26
     kedua
    0.25
    Act Density 0.078%

    No Known Activations