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

    Neuronpedia

    INDEX
    Explanations

    trust

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     экспорт
    -0.10
     прибыль
    -0.09
     площадь
    -0.09
     aluminio
    -0.09
    面积
    -0.09
     Gutenberg
    -0.08
     сорт
    -0.08
     rake
    -0.08
     atrap
    -0.08
     гриб
    -0.08
    POSITIVE LOGITS
     বন্ধু
    0.14
     acquaintances
    0.13
    friends
    0.12
     நண்ப
    0.12
     amigos
    0.12
     vrienden
    0.11
     मित्र
    0.11
    neighbors
    0.11
     friends
    0.11
     Freunde
    0.11
    Act Density 0.060%

    No Known Activations