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

    Neuronpedia

    INDEX
    Explanations

    physical and mathematical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ter
    0.83
    :>
    0.81
     mercado
    0.74
    这部
    0.73
    +
    0.73
     Jahre
    0.72
     sicher
    0.71
     lbs
    0.71
     seleccione
    0.71
     lb
    0.71
    POSITIVE LOGITS
    ﺣ
    0.86
    ﻣ
    0.86
     chromedp
    0.83
    ኩል
    0.83
     ${(
    0.77
    𝐒
    0.76
     $(\
    0.76
     distinguishes
    0.75
    colato
    0.75
     Λ
    0.75
    Act Density 0.214%

    No Known Activations