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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ಿಸಿದ್ದ
    -0.08
    ಿಸಿದ
    -0.08
     Uniform
    -0.07
    ्ट
    -0.07
    เต็ม
    -0.07
     المورد
    -0.07
     attainment
    -0.07
    บัญ
    -0.07
    ಿಸಿ
    -0.07
    teilen
    -0.07
    POSITIVE LOGITS
     Lucas
    0.08
    <|reserved_200016|>
    0.08
     یہ
    0.08
    779
    0.08
    ergency
    0.07
     Neville
    0.07
     ਇਹ
    0.07
     mano
    0.07
    、生
    0.07
     dolore
    0.07
    Act Density 0.011%

    No Known Activations