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

    Neuronpedia

    INDEX
    Explanations

    Modern [fields]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ok
    0.48
     هنگ
    0.44
    。</
    0.43
     kogu
    0.41
     đông
    0.39
     Easily
    0.39
    阴
    0.39
     during
    0.39
     stored
    0.38
    or
    0.38
    POSITIVE LOGITS
     moderne
    0.78
     modernen
    0.73
     conveniences
    0.72
    izr
    0.71
    izing
    0.71
     현대
    0.70
     modernes
    0.68
    isiert
    0.66
     sensibilities
    0.66
    Modern
    0.64
    Act Density 0.009%

    No Known Activations