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

    Neuronpedia

    INDEX
    Explanations

    most widely supported browser features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     integrable
    0.49
     interfacing
    0.48
     integr
    0.46
    Interfaz
    0.46
     interface
    0.44
     interfaces
    0.43
     interacting
    0.42
     интегра
    0.42
     integrate
    0.41
     Integr
    0.41
    POSITIVE LOGITS
     poly
    0.77
    polyfills
    0.70
     Poly
    0.68
     IE
    0.66
    Feature
    0.64
    Poly
    0.63
    polyfill
    0.63
     sh
    0.60
     Feature
    0.59
     feature
    0.57
    Act Density 0.028%

    No Known Activations