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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मल्टी
    0.40
     STORY
    0.40
     terap
    0.39
     उद्देश्यों
    0.39
    པ་
    0.38
    ミン
    0.38
    Textures
    0.38
    Story
    0.37
    ვნ
    0.37
     अवधि
    0.37
    POSITIVE LOGITS
     flammable
    0.40
     easements
    0.40
     bumpers
    0.39
     Airbus
    0.39
     wig
    0.39
     wiggle
    0.39
     elegant
    0.39
     asp
    0.39
     eddy
    0.38
     entrants
    0.38
    Act Density 0.017%

    No Known Activations