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

    Neuronpedia

    INDEX
    Explanations

    Non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ávky
    -0.08
    вая
    -0.07
     jste
    -0.07
     HI
    -0.06
    ativas
    -0.06
    유
    -0.06
    鋼
    -0.06
    梦
    -0.06
    _nbr
    -0.06
    ━━
    -0.06
    POSITIVE LOGITS
    bfd
    0.07
    -offset
    0.07
     "\
    0.07
     aktar
    0.07
     государ
    0.07
     kazanç
    0.07
    .ค
    0.06
     mạng
    0.06
    Contrib
    0.06
    _month
    0.06
    Act Density 0.275%

    No Known Activations