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

    Neuronpedia

    INDEX
    Explanations

    -ian, -ian, -ki, -li, U-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    1.60
    or
    1.31
    1
    1.25
    p
    1.24
    of
    1.21
    ل
    1.21
    ре
    1.17
    ва
    1.17
    at
    1.16
    ag
    1.15
    POSITIVE LOGITS
    는
    1.22
     not
    1.08
     Jews
    0.99
    はどう
    0.96
     Ō
    0.94
    )."
    0.90
     moths
    0.90
     від
    0.87
     Himalayas
    0.86
     کل
    0.85
    Act Density 0.000%

    No Known Activations