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

    Neuronpedia

    INDEX
    Explanations

    define/denote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     realtor
    -0.08
     거의
    -0.08
     hampir
    -0.08
     Rou
    -0.08
     разум
    -0.08
     encamin
    -0.08
     tender
    -0.08
     secondo
    -0.08
     కుమ
    -0.07
     עומ
    -0.07
    POSITIVE LOGITS
    Notation
    0.12
     notation
    0.12
    notation
    0.11
     denotes
    0.09
     shorthand
    0.09
     denote
    0.09
     tuples
    0.09
     letters
    0.09
    notations
    0.09
    Variables
    0.08
    Act Density 0.055%

    No Known Activations