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

    Neuronpedia

    INDEX
    Explanations

    parentheses and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Director
    -0.07
    \Builder
    -0.07
    ynet
    -0.07
     raining
    -0.06
     screamed
    -0.06
    >equals
    -0.06
     日
    -0.06
     cider
    -0.06
    .reserve
    -0.06
    cg
    -0.06
    POSITIVE LOGITS
    leniyor
    0.06
    (shader
    0.06
    mayacak
    0.06
     ControllerBase
    0.06
    [...,
    0.06
     шаг
    0.06
    ochond
    0.06
    kového
    0.06
    ootball
    0.06
    uous
    0.06
    Act Density 0.001%

    No Known Activations