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

    Neuronpedia

    INDEX
    Explanations

    how to explain concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نسب
    0.43
     misuse
    0.42
     medieval
    0.41
     need
    0.41
     bastard
    0.40
     uphold
    0.39
     pupils
    0.38
     accusation
    0.38
     protop
    0.38
     indire
    0.38
    POSITIVE LOGITS
    フォーマンス
    0.47
    ல்
    0.42
     Polytechnique
    0.42
    EnglishMarks
    0.42
    आरओ
    0.41
    ⌔
    0.40
    ℠
    0.40
    ᴼ
    0.40
    WinCounter
    0.39
    跤
    0.39
    Act Density 0.001%

    No Known Activations