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

    Neuronpedia

    INDEX
    Explanations

    first things or prioritization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oras
    0.45
     링크
    0.41
    cmt
    0.40
     silic
    0.38
     لینک
    0.38
    сный
    0.38
    érale
    0.38
     link
    0.37
     folgenden
    0.37
     bắc
    0.37
    POSITIVE LOGITS
    先に
    0.82
     먼저
    0.77
    先
    0.74
     zuerst
    0.74
     eerst
    0.66
     сначала
    0.63
    先把
    0.62
    首先
    0.62
     先
    0.62
     først
    0.61
    Act Density 0.149%

    No Known Activations