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

    Neuronpedia

    INDEX
    Explanations

    at the end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     স্থগিত
    0.80
     dupa
    0.78
     meydana
    0.74
    nade
    0.70
     gebracht
    0.67
    Anagram
    0.66
    ランク
    0.66
     hlad
    0.65
    annel
    0.65
    zwischen
    0.65
    POSITIVE LOGITS
     case
    0.72
     Case
    0.70
     How
    0.68
    ज़र
    0.65
     Field
    0.65
    <unused752>
    0.65
    getSave
    0.64
     ಇದಕ್ಕೆ
    0.64
     Mission
    0.62
     Git
    0.62
    Act Density 0.041%

    No Known Activations