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

    Neuronpedia

    INDEX
    Explanations

    verse references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Francisco
    0.52
    Francisco
    0.50
    推动
    0.48
    のみ
    0.46
     silenz
    0.46
    inizin
    0.46
    目錄
    0.46
    ഞ്ചി
    0.45
    ıyla
    0.45
    Whenever
    0.44
    POSITIVE LOGITS
     сове
    0.64
    ज
    0.61
     سه
    0.60
     ++)
    0.56
    _{+
    0.53
    ᕋ
    0.53
     lymphatiques
    0.53
     ባ
    0.52
     염
    0.52
     सज
    0.52
    Act Density 0.000%

    No Known Activations