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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IGN
    -0.07
    [test
    -0.07
     Mob
    -0.07
    olumes
    -0.07
    <Class
    -0.07
     fuera
    -0.07
     ages
    -0.07
     MPL
    -0.07
    违章
    -0.07
     האש
    -0.07
    POSITIVE LOGITS
    bo
    0.07
    лет
    0.06
    роб
    0.06
    前の
    0.06
    而不是
    0.06
     receiver
    0.06
    ካ
    0.06
    ?
    0.06
    �
    0.06
     @"
    0.06
    Act Density 0.002%

    No Known Activations