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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icals
    -0.07
     مثلا
    -0.06
    ILA
    -0.06
     Анг
    -0.06
    �
    -0.06
     ['-
    -0.06
    textBox
    -0.06
    .Expressions
    -0.06
     '-
    -0.06
     vět
    -0.06
    POSITIVE LOGITS
    .advance
    0.07
     sloppy
    0.06
    intColor
    0.06
     dissolved
    0.06
     خواه
    0.06
    /common
    0.06
    Realm
    0.06
    σία
    0.06
     βο
    0.06
     GC
    0.06
    Act Density 0.002%

    No Known Activations