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

    Neuronpedia

    INDEX
    Explanations

    shapes, math, clothing, plants, food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    1.00
    在
    0.89
    de
    0.87
    se
    0.82
     mikä
    0.82
     it
    0.79
    deki
    0.78
    いい
    0.77
    ication
    0.70
    ใน
    0.70
    POSITIVE LOGITS
    ва
    1.45
    ни
    1.35
    т
    1.22
    ри
    1.21
    ৫
    1.12
    تين
    1.07
    ви
    1.04
    ير
    1.03
    il
    1.02
    ко
    1.02
    Act Density 0.040%

    No Known Activations