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

    Neuronpedia

    INDEX
    Explanations

    noun or word replacement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     آسی
    0.87
     geometri
    0.85
     geometrically
    0.82
     часы
    0.82
    PLEMENT
    0.81
    ༘
    0.80
     slidesToShow
    0.79
     hairdry
    0.79
    घड
    0.77
     मैथमेटिक्स
    0.77
    POSITIVE LOGITS
    e
    0.79
    t
    0.79
    ei
    0.76
    തിനാൽ
    0.72
     B
    0.70
    ${
    0.70
    ii
    0.69
    MN
    0.69
    agens
    0.68
    ak
    0.68
    Act Density 0.000%

    No Known Activations