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

    Neuronpedia

    INDEX
    Explanations

    dates and ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Already
    0.36
    uyi
    0.36
    Already
    0.33
    আমরা
    0.33
    already
    0.33
     unauthorised
    0.32
     سابقا
    0.32
     already
    0.32
    ────────────────
    0.32
    ᆞ
    0.32
    POSITIVE LOGITS
     vrchol
    0.43
     ድረስ
    0.43
    結束
    0.40
    下旬
    0.40
     දක්
    0.39
    ми
    0.39
     पर्यंत
    0.39
     infinity
    0.38
     infinito
    0.38
    为止
    0.38
    Act Density 0.128%

    No Known Activations