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

    Neuronpedia

    INDEX
    Explanations

    prohibited responses that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    जिसे
    0.48
    機構
    0.40
     کجا
    0.40
    যার
    0.40
     এলাম
    0.39
     posiblemente
    0.39
     seguramente
    0.38
    うち
    0.38
    வாள
    0.38
    member
    0.37
    POSITIVE LOGITS
     tế
    0.43
    ته
    0.40
     содержа
    0.38
     Tez
    0.38
     acknowledged
    0.38
    ohia
    0.37
    tgz
    0.37
    рито
    0.37
     zuk
    0.37
    teis
    0.37
    Act Density 0.016%

    No Known Activations