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

    Neuronpedia

    INDEX
    Explanations

    lil'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ция
    1.19
    ことなく
    1.15
    ról
    1.00
    تان
    0.90
    ет
    0.83
    ного
    0.83
    ли
    0.82
     готови
    0.82
     পরই
    0.80
    다면
    0.80
    POSITIVE LOGITS
     It
    1.49
     I
    1.38
    It
    1.34
    \
    1.30
     \
    1.30
     A
    1.20
    ي
    1.16
     R
    1.15
     S
    1.13
    n
    1.12
    Act Density 0.001%

    No Known Activations