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

    Neuronpedia

    INDEX
    Explanations

    post- words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    -2.39
     zwanzig
    -2.27
     to
    -2.20
    鹋
    -2.17
    也得
    -1.98
    摒
    -1.98
    氿
    -1.95
     zwölf
    -1.90
     This
    -1.84
    fantasia
    -1.81
    POSITIVE LOGITS
    Очень
    2.36
    桖
    2.31
    s
    2.14
     現貨
    2.09
     russes
    2.05
    i
    2.05
    櫚
    2.05
    鞴
    2.05
    Setelah
    2.02
    Пусть
    2.02
    Act Density 0.025%

    No Known Activations