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

    Neuronpedia

    INDEX
    Explanations

    clarification or definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ｆ
    0.44
     خی
    0.43
    wiek
    0.42
    ேத்க
    0.41
     Chorus
    0.40
    綽
    0.39
    FQ
    0.39
    Iris
    0.38
     iris
    0.38
     Iris
    0.38
    POSITIVE LOGITS
    ত্তা
    0.41
    UNDE
    0.40
    راس
    0.40
    ouser
    0.38
    ubert
    0.37
    تك
    0.37
     транспорти
    0.37
     огра
    0.37
    تش
    0.37
     destinado
    0.36
    Act Density 0.000%

    No Known Activations