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

    Neuronpedia

    INDEX
    Explanations

    ball physics and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ک
    1.15
    л
    1.13
    k
    1.09
    D
    1.01
    𝗯
    1.01
    кому
    0.99
    ні
    0.99
    ದ
    0.98
    も
    0.97
    मधील
    0.96
    POSITIVE LOGITS
     for
    1.11
     ball
    1.11
     Ball
    1.11
    0
    1.00
     BALL
    0.93
    <0x0D>
    0.90
     is
    0.80
     baller
    0.80
     or
    0.79
    ০০০
    0.78
    Act Density 0.016%

    No Known Activations