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

    Neuronpedia

    INDEX
    Explanations

    rating

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ratings
    0.68
     rating
    0.66
     dispatch
    0.59
    স্টার
    0.59
     sometimes
    0.57
     listing
    0.57
     spacing
    0.57
     dispatcher
    0.57
    rating
    0.57
     parchment
    0.57
    POSITIVE LOGITS
     المنتج
    0.63
    getError
    0.63
    納得
    0.63
    Rational
    0.59
     normes
    0.59
    enov
    0.58
    バリ
    0.57
    欄
    0.57
     ब्रेक
    0.57
    Produkt
    0.57
    Act Density 0.005%

    No Known Activations