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

    Neuronpedia

    INDEX
    Explanations

    understands nuance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mantém
    0.44
    並沒有
    0.44
     による
    0.43
     stderr
    0.43
    harvard
    0.43
    odymyr
    0.42
     клуба
    0.42
     Unlike
    0.40
     谢
    0.40
    ुरू
    0.39
    POSITIVE LOGITS
     desire
    0.53
    ing
    0.51
     reworked
    0.46
     torrential
    0.46
     geniuses
    0.46
     precipitation
    0.45
     transitory
    0.45
    ೋ
    0.43
    autres
    0.43
     purpos
    0.43
    Act Density 0.000%

    No Known Activations