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

    Neuronpedia

    INDEX
    Explanations

    code diff markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ㄣ
    0.42
    StillWater
    0.39
    Simpson
    0.37
    넬
    0.37
    uidade
    0.36
     bao
    0.35
     ጉ
    0.35
     পড়িল
    0.35
    $};
    0.35
    globin
    0.34
    POSITIVE LOGITS
    @@
    0.51
    +
    0.41
    diff
    0.35
     silently
    0.34
     Index
    0.34
    +#
    0.34
    ＋
    0.33
    root
    0.32
    +//
    0.32
    +'
    0.31
    Act Density 0.000%

    No Known Activations