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

    Neuronpedia

    INDEX
    Explanations

    excessive qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ufficial
    1.04
     amici
    1.01
    ی
    0.98
    тив
    0.89
    ZIONE
    0.89
     بیاکت
    0.88
    );//
    0.88
    רות
    0.88
     articoli
    0.88
     attir
    0.88
    POSITIVE LOGITS
     (
    1.34
    .
    1.22
    v
    1.20
    at
    1.18
    al
    1.12
    너무
    1.11
    ون
    1.06
    ate
    1.02
    to
    1.02
    -
    1.02
    Act Density 0.023%

    No Known Activations