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

    Neuronpedia

    INDEX
    Explanations

    commercial lending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    描述
    0.45
    を表示
    0.39
     ador
    0.38
     photograph
    0.38
    文件
    0.38
     lign
    0.38
     ergonom
    0.37
    nourished
    0.37
     cittam
    0.37
    tores
    0.37
    POSITIVE LOGITS
    elyn
    0.44
    ଥ
    0.43
    elen
    0.40
    エリー
    0.37
     سكس
    0.37
     zerst
    0.37
    Builders
    0.37
    рах
    0.37
    Codec
    0.37
    Builder
    0.36
    Act Density 0.000%

    No Known Activations