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

    Neuronpedia

    INDEX
    Explanations

    specific topic or important elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鵃
    0.43
    же
    0.41
    䊂
    0.41
    ujah
    0.40
     Build
    0.38
    橿
    0.38
    स्टैंड
    0.38
    cherry
    0.38
    פת
    0.38
    天
    0.38
    POSITIVE LOGITS
     novembre
    0.39
     Dain
    0.38
     اش
    0.35
     mud
    0.35
     outubro
    0.35
     TInner
    0.35
     sóng
    0.34
     Finn
    0.33
     janeiro
    0.33
     רבים
    0.33
    Act Density 0.000%

    No Known Activations