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

    Neuronpedia

    INDEX
    Explanations

    5 followed by 6

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    伲
    0.33
    ൗ
    0.29
     therefore
    0.28
     Phal
    0.28
    интере
    0.26
     Therefore
    0.26
    Dh
    0.26
    豊富な
    0.26
     Wheels
    0.26
     Scaling
    0.25
    POSITIVE LOGITS
    oden
    0.35
    itz
    0.33
    igte
    0.33
    ilien
    0.32
    íncipe
    0.31
     المزيد
    0.31
    inhua
    0.31
    рін
    0.30
    <unused2121>
    0.30
    iedo
    0.30
    Act Density 0.016%

    No Known Activations