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

    Neuronpedia

    INDEX
    Explanations

    patch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    聽
    -0.07
    /an
    -0.06
    �
    -0.06
    .chars
    -0.06
    喑
    -0.06
     우
    -0.06
    łam
    -0.06
    �
    -0.06
     itr
    -0.06
    င
    -0.06
    POSITIVE LOGITS
    Sampling
    0.07
    低迷
    0.07
    ainties
    0.07
    (predictions
    0.07
    ETA
    0.07
    .subject
    0.07
    aju
    0.07
    滞
    0.07
     epis
    0.07
    бой
    0.07
    Act Density 0.015%

    No Known Activations