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

    Neuronpedia

    INDEX
    Explanations

    causes feelings or impressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     logarithmic
    0.45
    佻
    0.44
     व्यवस्थित
    0.44
    হি
    0.44
     feeder
    0.40
    ینڈ
    0.40
     meandering
    0.39
    遒
    0.39
     দিয়ে
    0.38
     logs
    0.38
    POSITIVE LOGITS
    感到
    0.97
    内心
    0.85
    不由
    0.79
    不禁
    0.78
    忍不住
    0.77
    心
    0.76
    激动
    0.76
    心中
    0.75
    觉得
    0.73
    รู้สึก
    0.72
    Act Density 0.005%

    No Known Activations