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

    Neuronpedia

    INDEX
    Explanations

    website domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     una
    0.69
    Y
    0.68
    div
    0.67
    Div
    0.64
    R
    0.63
    N
    0.62
    Int
    0.62
     une
    0.61
    May
    0.59
    sub
    0.59
    POSITIVE LOGITS
    <unused1866>
    1.01
    readthedocs
    0.96
    <unused1880>
    0.94
    торию
    0.90
     polytopes
    0.89
     disposit
    0.88
    遄
    0.88
    ຟ
    0.87
     ustawy
    0.87
    केंसी
    0.87
    Act Density 0.288%

    No Known Activations