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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    春
    -0.08
    by
    -0.08
    Я
    -0.07
     Grace
    -0.07
     آن
    -0.06
     asleep
    -0.06
    (observer
    -0.06
     зависимости
    -0.06
    該
    -0.06
     þ
    -0.06
    POSITIVE LOGITS
     레
    0.07
    ukkan
    0.06
    :end
    0.06
    :^(
    0.06
    Před
    0.06
    �
    0.06
     parach
    0.06
    Development
    0.06
    .SUB
    0.06
    ARGV
    0.06
    Act Density 0.014%

    No Known Activations