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

    Neuronpedia

    INDEX
    Explanations

    list items following commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sebagainya
    0.40
    …
    0.39
    等等
    0.38
     และ
    0.36
    。
    0.35
     등이
    0.34
     અને
    0.33
    ……”
    0.33
     .....
    0.32
    ・
    0.32
    POSITIVE LOGITS
     যেমন
    0.38
     જેમાં
    0.37
     включая
    0.36
     kuten
    0.36
     které
    0.36
     yakni
    0.36
     zoals
    0.35
     namely
    0.35
     including
    0.35
     کیونکہ
    0.35
    Act Density 0.226%

    No Known Activations