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

    Neuronpedia

    INDEX
    Explanations

    told, says, said, stating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Organization
    0.40
     Organization
    0.39
    ර්ථ
    0.39
     ชีวิต
    0.39
     angst
    0.38
    லாமல்
    0.38
     television
    0.38
     ऑर्ग
    0.38
     అన
    0.37
     இல்லாமல்
    0.37
    POSITIVE LOGITS
     sorry
    0.65
    sorry
    0.63
     Sorry
    0.62
    Sorry
    0.60
     due
    0.59
     policy
    0.59
    暂时
    0.56
     আপাতত
    0.56
    お客様
    0.54
     pihaknya
    0.54
    Act Density 0.011%

    No Known Activations