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

    Neuronpedia

    INDEX
    Explanations

    sponsorships and hashtags on social media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     מע
    0.48
     القط
    0.44
    นั้น
    0.43
     day
    0.42
    这份
    0.42
     दिन
    0.41
     보시면
    0.41
     टाइम
    0.41
     ভুট্টো
    0.40
     عنده
    0.40
    POSITIVE LOGITS
    rhein
    0.43
     amassed
    0.42
    0
    0.40
    amp
    0.39
    lés
    0.39
     रक्षाबंधनाच्या
    0.39
     A
    0.38
    ned
    0.38
    ociazione
    0.38
     accanto
    0.38
    Act Density 0.005%

    No Known Activations