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

    Neuronpedia

    INDEX
    Explanations

    numbers, units, symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estil
    0.47
    ANSAS
    0.42
     sinist
    0.42
    ებას
    0.39
    টিস
    0.39
    idxs
    0.38
    ంతో
    0.37
    atiya
    0.37
    тя
    0.37
     stylist
    0.37
    POSITIVE LOGITS
     Rel
    0.42
    Rel
    0.40
     Hurley
    0.39
     Aire
    0.37
    aven
    0.37
    avon
    0.36
     प्लेटफार्म
    0.35
     Sympt
    0.35
     Remed
    0.35
     olduğ
    0.34
    Act Density 0.036%

    No Known Activations