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

    Neuronpedia

    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     لن
    -0.07
    reported
    -0.07
    CppType
    -0.06
     مشاهدة
    -0.06
     squirrel
    -0.06
    ुआत
    -0.06
    нез
    -0.06
     заказ
    -0.06
     خواه
    -0.06
     spanish
    -0.06
    POSITIVE LOGITS
    _prim
    0.08
     Tol
    0.06
     Reich
    0.06
     tert
    0.06
    ::↵
    0.06
    reff
    0.06
     translucent
    0.06
     přes
    0.06
     temper
    0.06
    _eth
    0.06
    Act Density 0.458%

    No Known Activations