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

    Neuronpedia

    INDEX
    Explanations

    app module or context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ের
    1.70
    е
    1.59
    ../../
    1.53
    ો
    1.50
    מ
    1.50
    ര
    1.49
     lẽ
    1.47
    মন
    1.46
    getImageFolder
    1.45
    そも
    1.44
    POSITIVE LOGITS
    d
    1.96
    el
    1.91
    o
    1.90
    ir
    1.88
    ointees
    1.74
    uccino
    1.70
    க்கள்
    1.68
    د
    1.68
    و
    1.66
    elina
    1.58
    Act Density 0.019%

    No Known Activations