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

    Neuronpedia

    INDEX
    Explanations

    survey

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (where
    -0.07
     experience
    -0.07
     Ottawa
    -0.06
     svůj
    -0.06
    setAttribute
    -0.06
     bowling
    -0.06
    歡
    -0.06
    (GameObject
    -0.06
    -mode
    -0.06
     juven
    -0.06
    POSITIVE LOGITS
     feminism
    0.07
     Rapid
    0.06
     hindsight
    0.06
    cstdint
    0.06
    ones
    0.06
     attracted
    0.06
     graphics
    0.06
    .userdetails
    0.06
    Embedded
    0.06
    ле
    0.06
    Act Density 0.223%

    No Known Activations