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

    Neuronpedia

    INDEX
    Explanations

    salt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Higgins
    -0.08
     کلی
    -0.07
    ayas
    -0.07
    اده
    -0.07
    commission
    -0.07
    анси
    -0.07
    Cons
    -0.06
     getch
    -0.06
     أي
    -0.06
    义
    -0.06
    POSITIVE LOGITS
     blackmail
    0.06
    Quarter
    0.06
     multiline
    0.06
     distort
    0.06
    không
    0.06
    λια
    0.06
    ft
    0.06
    retain
    0.06
    _digit
    0.06
     DropDownList
    0.06
    Act Density 0.001%

    No Known Activations