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

    Neuronpedia

    INDEX
    Explanations

    semantical In

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺍ
    1.35
    ления
    1.34
    (
    1.23
    ars
    1.23
     \
    1.21
    ning
    1.16
    cs
    1.15
    t
    1.15
    ONG
    1.14
    ain
    1.13
    POSITIVE LOGITS
    า
    1.38
    ת
    1.38
    dır
    1.29
    지
    1.20
    ல்
    1.11
    ור
    1.11
     homenaje
    1.07
    )&=
    1.06
    ர்
    1.03
    ной
    1.02
    Act Density 0.001%

    No Known Activations