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

    Neuronpedia

    INDEX
    Explanations

    INTO

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    1.23
    or
    1.17
    ia
    1.14
    ﻥ
    1.14
    oon
    1.10
    覀
    1.07
    ik
    1.05
    ின்
    1.05
    ai
    1.02
    A
    1.02
    POSITIVE LOGITS
     informática
    1.12
    𝘀
    1.12
     Eller
    1.11
     কিংবা
    1.10
    𝟰
    1.08
     ৪
    1.07
     ס
    1.07
     अथवा
    1.06
     bądź
    1.06
    ร้อง
    1.05
    Act Density 0.175%

    No Known Activations