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

    Neuronpedia

    INDEX
    Explanations

    death threat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Marie
    0.49
    न
    0.46
    Object
    0.44
    學生
    0.42
     MRS
    0.42
     ഖ
    0.41
    ა
    0.41
     MLA
    0.41
     оста
    0.40
     индекс
    0.40
    POSITIVE LOGITS
     exige
    0.45
     tranquilo
    0.44
    њу
    0.43
    संगिक
    0.43
    𝜁
    0.43
    確認
    0.43
     prairies
    0.42
     requiere
    0.41
     nécessite
    0.41
    助
    0.41
    Act Density 0.008%

    No Known Activations