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

    Neuronpedia

    INDEX
    Explanations

    body processes and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا۔
    0.49
    AMAN
    0.48
     separación
    0.47
    на
    0.46
     шко
    0.46
     глубо
    0.46
     étamines
    0.45
     magní
    0.43
    am
    0.43
    ubo
    0.43
    POSITIVE LOGITS
    t
    0.48
     الجسم
    0.46
    r
    0.46
    ing
    0.45
     on
    0.44
    l
    0.44
     kroppen
    0.43
     oxidative
    0.43
     illness
    0.43
     S
    0.42
    Act Density 0.008%

    No Known Activations