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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     supervised
    -0.07
    leasing
    -0.07
    .CreateDirectory
    -0.07
     resisted
    -0.07
    ίες
    -0.06
     oversees
    -0.06
     ange
    -0.06
    分别
    -0.06
    quipe
    -0.06
    ии
    -0.06
    POSITIVE LOGITS
    OBJECT
    0.07
     вида
    0.06
     Inspiration
    0.06
    NAV
    0.06
    .flowLayoutPanel
    0.06
     ()->
    0.06
    ımızı
    0.06
     ESC
    0.06
    AILY
    0.06
     [("
    0.06
    Act Density 0.049%

    No Known Activations