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

    Neuronpedia

    INDEX
    Explanations

    miscellaneous other categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.31
    [
    0.30
    It
    0.29
    this
    0.29
    He
    0.29
    "
    0.28
    <
    0.28
    0.28
    Ob
    0.27
    This
    0.27
    POSITIVE LOGITS
     Miscellaneous
    0.37
     miscellaneous
    0.35
     その他
    0.33
     प्रश्‍
    0.28
     Misc
    0.28
     ಇರುವ
    0.27
     egyéb
    0.27
     기타
    0.27
     अन्य
    0.26
     อื่น
    0.26
    Act Density 0.170%

    No Known Activations