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

    Neuronpedia

    INDEX
    Explanations

    bad ideas and warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ūn
    0.43
    BK
    0.42
    akaan
    0.41
     ук
    0.41
    Ụ
    0.41
    .,
    0.40
    </em>
    0.39
    PG
    0.39
    9
    0.39
    ائه
    0.39
    POSITIVE LOGITS
     idios
    0.45
    捪
    0.45
    志森
    0.45
    兗
    0.44
     Giuseppe
    0.44
     Veja
    0.43
     Pause
    0.43
    瑭
    0.43
    忪
    0.42
     त्रिपुरा
    0.42
    Act Density 0.001%

    No Known Activations