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

    Neuronpedia

    INDEX
    Explanations

    Polish or Russian language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stores
    -0.08
    DEFINE
    -0.08
    -sizing
    -0.07
     menjaga
    -0.07
    sete
    -0.07
    keepers
    -0.07
     blem
    -0.07
    �
    -0.07
    karma
    -0.07
     desal
    -0.07
    POSITIVE LOGITS
     языке
    0.12
    -English
    0.11
     الإنجليزية
    0.10
    英语
    0.10
    อังกฤษ
    0.10
     العربية
    0.10
     Gymraeg
    0.10
     inglés
    0.10
     فارسی
    0.09
     لغة
    0.09
    Act Density 0.027%

    No Known Activations