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

    Neuronpedia

    INDEX
    Explanations

    expansion and growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    들도
    0.44
     moglie
    0.43
    ط
    0.43
     comune
    0.42
    nord
    0.41
    睹
    0.41
    ハンドル
    0.41
    ос
    0.41
    NYC
    0.41
    osphere
    0.40
    POSITIVE LOGITS
     Expand
    0.50
     expansions
    0.43
     TextAlign
    0.43
     expands
    0.43
     Freezer
    0.42
     ն
    0.42
    Expansion
    0.41
     Expanding
    0.40
     Bara
    0.40
     Nếu
    0.39
    Act Density 0.000%

    No Known Activations