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

    Neuronpedia

    INDEX
    Explanations

    mugs and print products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     incomple
    0.45
     interdependence
    0.43
     nutrients
    0.43
    ディレクトリ
    0.43
    韮
    0.42
     intellect
    0.42
    ramework
    0.41
     circumcision
    0.39
    NonQuery
    0.39
    Nonnull
    0.39
    POSITIVE LOGITS
     mugs
    0.76
     mug
    0.68
     Canvas
    0.65
     canvas
    0.63
     Mug
    0.61
    Canvas
    0.57
     canvases
    0.54
     poster
    0.52
     products
    0.52
     Print
    0.52
    Act Density 0.002%

    No Known Activations