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

    Neuronpedia

    INDEX
    Explanations

    show me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     طور
    0.43
    Ⴝ
    0.42
    وء
    0.41
    prote
    0.40
     Towards
    0.39
    ن
    0.38
     šk
    0.38
    软件
    0.38
    اموش
    0.37
    น่า
    0.37
    POSITIVE LOGITS
    stopper
    0.74
    reel
    0.64
    manship
    0.61
    piece
    0.58
     casing
    0.58
    runners
    0.58
     us
    0.57
    case
    0.57
    stopping
    0.57
     stopper
    0.53
    Act Density 0.027%

    No Known Activations