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

    Neuronpedia

    INDEX
    Explanations

    headlines and articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geliştir
    0.52
     adı
    0.51
    öse
    0.48
    hitth
    0.48
    ülő
    0.48
     gelişt
    0.48
    <unused530>
    0.47
    éi
    0.47
    dört
    0.46
     Religious
    0.46
    POSITIVE LOGITS
    t
    0.55
    O
    0.51
    і
    0.48
    S
    0.46
    R
    0.45
    E
    0.44
    C
    0.43
    e
    0.42
    re
    0.41
    c
    0.41
    Act Density 0.008%

    No Known Activations