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

    Neuronpedia

    INDEX
    Explanations

    hotel name or product manager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    0.82
    antina
    0.79
    [
    0.78
    போன்ற
    0.77
    {
    0.77
    "$
    0.76
    ó
    0.74
    ı
    0.72
    িল
    0.72
    ')
    0.71
    POSITIVE LOGITS
     harmonious
    0.91
     männer
    0.91
     cuddling
    0.86
    用户
    0.83
    ﻐ
    0.79
     wohn
    0.79
    用户信息
    0.79
     ۾
    0.78
     collapsing
    0.76
     superfluous
    0.76
    Act Density 0.000%

    No Known Activations