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

    Neuronpedia

    INDEX
    Explanations

    damp dampening dampness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    1.70
    and
    1.50
    ah
    1.48
    ong
    1.47
    ä
    1.47
    et
    1.36
    on
    1.21
    ing
    1.20
    ed
    1.19
    ن
    1.18
    POSITIVE LOGITS
    the
    1.07
     =
    1.05
    dır
    1.02
     Спорттук
    1.00
    ي
    0.97
     verwend
    0.96
    ്യ
    0.95
    のを
    0.94
    ාවිත
    0.94
    yı
    0.93
    Act Density 0.000%

    No Known Activations