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

    Neuronpedia

    INDEX
    Explanations

    Versal, Pass, treaty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تي
    1.30
    ק
    1.13
    সহ
    1.06
    يش
    1.05
    м
    1.05
    ي
    1.05
    ד
    1.04
    ז
    1.04
    سي
    1.03
    7
    1.02
    POSITIVE LOGITS
    ot
    1.15
    ’
    1.06
    otar
    1.02
    us
    1.00
    ol
    1.00
    ۱
    0.99
    ри
    0.96
    рия
    0.92
    1
    0.92
    １
    0.89
    Act Density 0.000%

    No Known Activations