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

    Neuronpedia

    INDEX
    Explanations

    abuse or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RasterModelGrid
    0.47
     छठी
    0.45
    𒂠
    0.43
    ຫນ
    0.40
    蓽
    0.40
     Вікі
    0.40
    ६
    0.39
    нуу
    0.39
     }^{*}
    0.39
    ಬ್ಬಳ್ಳಿ
    0.39
    POSITIVE LOGITS
    ,
    0.50
    .
    0.49
    ;
    0.46
    ，
    0.46
     during
    0.46
     when
    0.45
     in
    0.43
     أثناء
    0.43
     of
    0.43
    ‚
    0.42
    Act Density 0.051%

    No Known Activations