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

    Neuronpedia

    INDEX
    Explanations

    short, direct, content topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нено
    0.46
    渽
    0.45
    MORD
    0.40
    Ⲧ
    0.40
    容量
    0.40
     Minn
    0.39
     مالک
    0.39
    INOIS
    0.39
    ہوری
    0.39
     काला
    0.39
    POSITIVE LOGITS
    almost
    0.42
    Almost
    0.42
    ars
    0.41
    Portrait
    0.40
    portrait
    0.39
    ranks
    0.39
    left
    0.38
    Old
    0.38
     almost
    0.38
    weapons
    0.38
    Act Density 0.000%

    No Known Activations