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

    Neuronpedia

    INDEX
    Explanations

    estimated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மொழ
    0.39
    aparikkh
    0.38
     אר
    0.37
    ט
    0.36
     фигу
    0.35
    様々な
    0.35
    Ку
    0.35
    Either
    0.35
    ụng
    0.35
    ಷ
    0.35
    POSITIVE LOGITS
     የ
    0.78
     የእ
    0.42
     DPRD
    0.42
    mrow
    0.42
     BTW
    0.40
     the
    0.40
     RoHS
    0.40
     ItemStack
    0.38
     motorcycle
    0.38
     eastbound
    0.38
    Act Density 0.187%

    No Known Activations