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

    Neuronpedia

    INDEX
    Explanations

    character introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hilarious
    1.19
     gourmet
    1.08
     fierce
    1.07
     gangster
    1.05
     menacing
    1.02
     humorous
    1.01
     gangsters
    1.01
     scandal
    1.00
     disguised
    1.00
     witty
    1.00
    POSITIVE LOGITS
    ீர்கள்
    0.90
     każdego
    0.84
    ﹂
    0.84
    ೀಯ
    0.83
     없다
    0.83
    istemas
    0.83
     있습니다
    0.82
    removeAttr
    0.81
    籹
    0.80
    ﻻ
    0.80
    Act Density 0.097%

    No Known Activations