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

    Neuronpedia

    INDEX
    Explanations

    specific language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .webp
    -0.09
     gastos
    -0.09
     DOJ
    -0.08
     investigar
    -0.08
     race
    -0.08
     randomly
    -0.08
    .jpeg
    -0.08
    .jpg
    -0.08
     shafts
    -0.08
     realistically
    -0.08
    POSITIVE LOGITS
     syntax
    0.14
     языке
    0.13
     لغة
    0.13
     язык
    0.13
     ಭಾಷ
    0.13
     ഭാഷ
    0.13
     языка
    0.13
     Sprache
    0.13
     زبان
    0.13
    语言
    0.12
    Act Density 0.021%

    No Known Activations