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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grips
    -0.07
    :
↵
↵
    -0.07
     wagon
    -0.07
    razy
    -0.07
    .ColumnStyles
    -0.07
     narrator
    -0.07
    	uv
    -0.07
     reels
    -0.07
    Box
    -0.06
    .all
    -0.06
    POSITIVE LOGITS
    aison
    0.06
    Scotland
    0.06
     Agreement
    0.06
    (PATH
    0.06
     misleading
    0.05
     yıldır
    0.05
     líder
    0.05
    isson
    0.05
    ../../
    0.05
     buttonText
    0.05
    Act Density 0.030%

    No Known Activations