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

    Neuronpedia

    INDEX
    Explanations

    Too good to be true

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "/";↵
    -0.09
    ("/");↵
    -0.09
     ido
    -0.08
     Parliamentary
    -0.08
     presos
    -0.08
     الشت
    -0.08
     orden
    -0.07
     pressing
    -0.07
     fonds
    -0.07
     minggu
    -0.07
    POSITIVE LOGITS
     suspicious
    0.15
     unrealistic
    0.13
     unusually
    0.13
     sudden
    0.13
    突然
    0.13
     improbable
    0.12
     sospe
    0.11
     unnatural
    0.11
     unusual
    0.11
     suddenly
    0.11
    Act Density 0.060%

    No Known Activations