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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     méth
    -0.07
    (bc
    -0.06
     Ire
    -0.06
    приклад
    -0.06
    .Return
    -0.06
    )[
    -0.06
     intermediary
    -0.06
    ）的
    -0.06
     ridge
    -0.06
     주
    -0.06
    POSITIVE LOGITS
    atican
    0.07
     suppose
    0.07
    ै.↵
    0.06
     submerged
    0.06
    ск
    0.06
     Funk
    0.06
    抬
    0.06
     Cheer
    0.06
    Questions
    0.06
    _image
    0.06
    Act Density 0.009%

    No Known Activations