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

    Neuronpedia

    INDEX
    Explanations

    closing parentheses and colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ịt
    1.33
     голову
    1.24
    правления
    1.20
    關係
    1.20
    ю
    1.19
     পত্রিকা
    1.16
    ify
    1.15
     ऋण
    1.14
    رس
    1.14
    ும்
    1.13
    POSITIVE LOGITS
     looms
    1.54
     seams
    1.49
     wallpapers
    1.46
     Jacq
    1.44
     Além
    1.37
    toare
    1.37
    ృష్టి
    1.37
    𝐳
    1.35
    y
    1.34
     hairline
    1.31
    Act Density 0.001%

    No Known Activations