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

    Neuronpedia

    INDEX
    Explanations

    drinks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fat
    -0.07
     bread
    -0.07
    326
    -0.07
     Clown
    -0.07
    324
    -0.07
    (index
    -0.06
    cale
    -0.06
    ulsion
    -0.06
     incentives
    -0.06
     Fat
    -0.06
    POSITIVE LOGITS
     Northern
    0.06
    Difficulty
    0.06
    ंक
    0.06
     провести
    0.06
    .destroy
    0.06
     kurum
    0.06
     instantiation
    0.06
     Afrika
    0.06
     хроничес
    0.06
    ClearColor
    0.05
    Act Density 0.018%

    No Known Activations