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

    Neuronpedia

    INDEX
    Explanations

    code imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cloves
    0.48
     tiene
    0.46
     እየሱስ
    0.46
     angin
    0.45
    centage
    0.44
     valves
    0.43
     firewood
    0.43
    zonych
    0.43
     pemb
    0.43
    bleeds
    0.43
    POSITIVE LOGITS
    0.49
     UIKit
    0.45
     Vereinigten
    0.39
     Bauhaus
    0.39
     básicos
    0.38
     Stamford
    0.38
     United
    0.37
    していた
    0.37
     К
    0.37
    тук
    0.37
    Act Density 0.002%

    No Known Activations