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

    Neuronpedia

    INDEX
    Explanations

    not possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hjälp
    0.43
     semoga
    0.43
     emphasize
    0.42
     നല്ല
    0.41
     подчер
    0.41
     aiuta
    0.41
    ("["
    0.39
     deinem
    0.39
     bør
    0.39
    強化
    0.38
    POSITIVE LOGITS
    无法
    0.92
     inability
    0.90
     невозможно
    0.90
    無法
    0.89
     impossible
    0.88
     impossibility
    0.84
     unable
    0.84
     impractical
    0.80
     imposs
    0.79
    impossible
    0.78
    Act Density 0.175%

    No Known Activations