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

    Neuronpedia

    INDEX
    Explanations

    floor and deployment terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.23
    f
    1.22
    d
    1.20
    s
    1.02
    p
    1.02
    the
    0.97
    ﺮ
    0.96
    ﺲ
    0.89
    st
    0.89
    dı
    0.87
    POSITIVE LOGITS
    า
    0.92
     maail
    0.91
     aspectos
    0.85
     edad
    0.80
    รุ่น
    0.79
    การ
    0.78
     durumda
    0.78
    ว่า
    0.77
    ä
    0.77
    ਨ
    0.77
    Act Density 0.020%

    No Known Activations