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

    Neuronpedia

    INDEX
    Explanations

    marking and names starting with mar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ع
    1.63
    H
    1.42
    ED
    1.38
    T
    1.30
    na
    1.30
    k
    1.28
    EL
    1.25
    一种
    1.24
    一些
    1.23
    ي
    1.23
    POSITIVE LOGITS
    ى
    1.21
    𝐞
    1.18
    ну
    1.13
    も
    1.08
    ും
    1.01
    eau
    1.00
    чи
    0.98
    િ
    0.98
    effects
    0.97
    euler
    0.96
    Act Density 0.265%

    No Known Activations