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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ྩ
    1.16
    ྐ
    1.02
    -”
    0.98
    …"
    0.95
    \\"
    0.95
     justement
    0.94
     Apesar
    0.94
    𝘁
    0.94
     있는
    0.93
    𝒐
    0.93
    POSITIVE LOGITS
    에
    1.04
    특별시
    0.95
    ను
    0.87
     imbued
    0.87
    ΙΑ
    0.87
    КА
    0.84
    本発明
    0.84
    bollah
    0.83
    Î
    0.82
     reconsider
    0.81
    Act Density 0.214%

    No Known Activations