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

    Neuronpedia

    INDEX
    Explanations

    words starting with dis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     COUNTRY
    0.45
    走出
    0.39
     HAIR
    0.39
    }")
    0.38
    "]}
    0.38
     शैक्षिक
    0.38
     lige
    0.37
    *}$
    0.37
    一層
    0.37
    穼
    0.36
    POSITIVE LOGITS
     Dis
    1.05
    Dis
    1.01
    dis
    0.96
     dis
    0.84
    DIS
    0.78
     DIS
    0.73
     disen
    0.68
     ディ
    0.65
     diſ
    0.62
     дис
    0.61
    Act Density 0.054%

    No Known Activations