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

    Neuronpedia

    INDEX
    Explanations

    words starting with el

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ották
    0.71
     totality
    0.69
    ل
    0.67
    ទាំង
    0.65
    ták
    0.65
    ت
    0.65
    y
    0.64
    RootNamespace
    0.64
    d
    0.63
    yld
    0.62
    POSITIVE LOGITS
    aboration
    1.06
     ouvrages
    0.89
    éments
    0.88
     народного
    0.86
     avance
    0.86
     uur
    0.84
     Oekra
    0.84
    ixir
    0.83
     ड
    0.83
    ías
    0.80
    Act Density 0.016%

    No Known Activations