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

    Neuronpedia

    INDEX
    Explanations

    multi-lingual content indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    か
    0.45
    ك
    0.42
    ed
    0.39
    aaa
    0.38
    aaaa
    0.36
    पणे
    0.35
     माझ्या
    0.35
    s
    0.35
    một
    0.33
    تك
    0.33
    POSITIVE LOGITS
     to
    0.44
    습니다
    0.38
     کی
    0.36
     είναι
    0.36
     ט
    0.35
     키
    0.35
    INE
    0.34
    ון
    0.34
     데이터
    0.34
     추가
    0.34
    Act Density 1.817%

    No Known Activations