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

    Neuronpedia

    INDEX
    Explanations

    another or new

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.32
    炜
    0.30
    $
    0.29
     Trailer
    0.28
    Ошибка
    0.28
    :
    0.28
    Westinghouse
    0.27
    ி
    0.27
    0.27
     Estado
    0.27
    POSITIVE LOGITS
    than
    0.34
     niż
    0.33
     একইভাবে
    0.30
    ţin
    0.30
     უფრო
    0.30
    同様
    0.27
     serupa
    0.27
     비슷한
    0.27
    Similarly
    0.27
    することも
    0.27
    Act Density 0.054%

    No Known Activations