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

    Neuronpedia

    INDEX
    Explanations

    truffle, tqdm, mushroom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     నీ
    0.40
     normalized
    0.40
    สวน
    0.40
     చె
    0.39
     Neighbor
    0.39
    这一点
    0.38
     ни
    0.37
     絵
    0.37
     kona
    0.37
    ))))
    0.37
    POSITIVE LOGITS
     truffle
    1.21
     Tru
    0.87
     tru
    0.67
    Tru
    0.66
    tru
    0.66
     tqdm
    0.64
     tr
    0.62
    ruff
    0.55
    mushroom
    0.52
     mushroom
    0.49
    Act Density 0.006%

    No Known Activations