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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     国
    -0.07
     вся
    -0.06
    υ
    -0.06
     rev
    -0.06
    。あ
    -0.06
    .combine
    -0.06
     optimistic
    -0.06
     Hawks
    -0.06
    ویزی
    -0.06
     حيث
    -0.06
    POSITIVE LOGITS
    рукту
    0.07
    formed
    0.07
    (arguments
    0.07
    number
    0.07
    _variable
    0.06
     صالح
    0.06
     warn
    0.06
    essage
    0.06
     Etsy
    0.06
     método
    0.06
    Act Density 0.000%

    No Known Activations