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

    Neuronpedia

    INDEX
    Explanations

    representation theory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    嚕
    0.41
    钚
    0.40
    acariy
    0.39
    廛
    0.38
     tenement
    0.38
     किरायेदारों
    0.38
    iduría
    0.38
    𝓮
    0.38
    犹如
    0.37
    擔
    0.37
    POSITIVE LOGITS
     representations
    0.88
     representation
    0.82
    representations
    0.77
     Representation
    0.75
     Representations
    0.74
    representation
    0.70
    Representation
    0.70
     representación
    0.59
     représentation
    0.58
     représent
    0.55
    Act Density 0.003%

    No Known Activations