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

    Neuronpedia

    INDEX
    Explanations

    metadata analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    原来的
    0.56
    大众
    0.48
    唐
    0.48
    ４
    0.47
    0.45
    τή
    0.44
    曾经
    0.43
    кол
    0.43
    伟
    0.43
    ད་
    0.43
    POSITIVE LOGITS
     hva
    0.49
     samtidig
    0.46
    fähigkeit
    0.46
     hvad
    0.45
     مدى
    0.45
     g
    0.45
     є
    0.45
    ostomy
    0.44
    alysis
    0.44
    ឍ
    0.44
    Act Density 0.001%

    No Known Activations