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

    Neuronpedia

    INDEX
    Explanations

    followed by comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    സും
    1.00
     illetve
    1.00
     maupun
    0.91
     että
    0.89
     diantaranya
    0.88
    などの
    0.86
     odnosno
    0.86
    等の
    0.83
    酲
    0.82
     گی۔
    0.81
    POSITIVE LOGITS
    ,
    4.13
    ，
    3.35
    ،
    3.14
     ,
    2.86
    ®,
    2.80
     ،
    2.72
    ™,
    2.67
    ,*
    2.63
    *,
    2.60
    **,
    2.57
    Act Density 7.664%

    No Known Activations