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
     dry
    -0.07
    Row
    -0.07
     controllers
    -0.07
     correct
    -0.07
    Folders
    -0.07
    <Menu
    -0.06
    <header
    -0.06
    -secondary
    -0.06
     reading
    -0.06
    丸
    -0.06
    POSITIVE LOGITS
    幾
    0.07
    หมาย
    0.07
     dapat
    0.06
     вел
    0.06
    -ajax
    0.06
     Sadly
    0.06
    はない
    0.06
    -settings
    0.06
    ，小
    0.06
    .Infof
    0.06
    Act Density 0.003%

    No Known Activations