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

    Neuronpedia

    INDEX
    Explanations

    vaccines, MIN, arrays, disk, times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ம்
    1.29
    eder
    1.29
    સ
    1.25
    iness
    1.23
    $
    1.23
    esses
    1.21
    दायी
    1.20
    opian
    1.20
    });
    1.19
    ury
    1.16
    POSITIVE LOGITS
    ط
    2.11
    তে
    1.76
    一股
    1.76
    ován
    1.70
     esperti
    1.64
    میں
    1.59
     există
    1.57
    ก
    1.56
    ä
    1.53
    не
    1.52
    Act Density 0.000%

    No Known Activations