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

    Neuronpedia

    INDEX
    Explanations

    Premium luxury goods

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parsing
    0.46
     epistemology
    0.43
     bootstrapping
    0.41
     metaphysics
    0.41
     recursion
    0.41
     orchestration
    0.41
     contextual
    0.40
     epistem
    0.40
     hypertext
    0.40
     adjacency
    0.40
    POSITIVE LOGITS
    Mini
    0.41
     aluminum
    0.41
    Smooth
    0.38
    premium
    0.38
    LN
    0.38
     mini
    0.38
    Vintage
    0.38
    小型
    0.38
    Luxury
    0.37
    Lemon
    0.37
    Act Density 0.277%

    No Known Activations