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

    Neuronpedia

    INDEX
    Explanations

    building genuine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Produced
    0.43
    lblCredits
    0.42
    ibli
    0.42
    ാപാ
    0.42
    uced
    0.41
    produced
    0.40
    fibre
    0.40
    ீர
    0.39
     ابي
    0.39
    𒂍
    0.39
    POSITIVE LOGITS
    BOARD
    0.41
     Bord
    0.40
     알
    0.40
     ngăn
    0.40
    ט
    0.39
     mogen
    0.39
    FIX
    0.38
    KO
    0.38
     Elo
    0.38
     direttamente
    0.37
    Act Density 0.000%

    No Known Activations