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

    Neuronpedia

    INDEX
    Explanations

    comical errors/mishaps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ug
    -0.07
    (dest
    -0.07
    izioni
    -0.07
     어느
    -0.07
     dak
    -0.06
    ("$
    -0.06
    -contained
    -0.06
    ویل
    -0.06
    _study
    -0.06
    σετε
    -0.06
    POSITIVE LOGITS
    _month
    0.07
     cords
    0.06
    εν
    0.06
    .GetSize
    0.06
     окон
    0.06
    ‍
    0.06
     메
    0.06
     didReceiveMemoryWarning
    0.06
     ním
    0.05
     blurry
    0.05
    Act Density 0.062%

    No Known Activations