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

    Neuronpedia

    INDEX
    Explanations

    affirmations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bạn
    0.46
     potete
    0.46
    എ
    0.45
     increí
    0.44
    ों
    0.44
    し
    0.43
    ご紹介
    0.43
    UIntValue
    0.43
     praticamente
    0.42
     güncelle
    0.42
    POSITIVE LOGITS
     and
    0.64
    in
    0.61
    ar
    0.58
    as
    0.57
    at
    0.57
    i
    0.55
     for
    0.54
     with
    0.53
     (
    0.51
    is
    0.48
    Act Density 0.001%

    No Known Activations