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

    Neuronpedia

    INDEX
    Explanations

    following numbers/words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resistência
    0.47
    学生
    0.47
    Merhaba
    0.47
    Players
    0.45
    œuvre
    0.45
     `{
    0.45
     gee
    0.44
     dogged
    0.44
     players
    0.44
     ম্যাচে
    0.44
    POSITIVE LOGITS
     distributing
    0.50
     allocating
    0.48
    ่
    0.47
    rines
    0.45
    tter
    0.45
    jakan
    0.44
    ITTER
    0.44
    ED
    0.44
    UD
    0.44
     ต้น
    0.43
    Act Density 0.000%

    No Known Activations