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

    Neuronpedia

    INDEX
    Explanations

    start of subject lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਆਂ
    0.32
     முதலிய
    0.32
    Generally
    0.32
     அதிகம்
    0.31
    arious
    0.30
    గిన
    0.30
     speaking
    0.30
    SCHRAMM
    0.30
     """",
    0.29
    ெல்லாம்
    0.29
    POSITIVE LOGITS
    Variant
    0.35
     Variant
    0.33
     variations
    0.32
     Sh
    0.30
     Var
    0.30
     Sche
    0.29
     variant
    0.29
     അവർ
    0.29
     Ше
    0.29
     Z
    0.28
    Act Density 0.066%

    No Known Activations