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

    Neuronpedia

    INDEX
    Explanations

    crucial to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sợi
    0.82
    ところ
    0.82
    ель
    0.81
    ué
    0.78
     tendrás
    0.78
     neurotrans
    0.77
    ற்புத
    0.77
    oncé
    0.77
     voldo
    0.75
     incrível
    0.75
    POSITIVE LOGITS
     ");
    0.90
     \
    0.87
    6
    0.87
    נ
    0.84
    Quem
    0.82
    Text
    0.81
     );
    0.79
    Org
    0.78
    IZED
    0.78
    Hand
    0.77
    Act Density 0.253%

    No Known Activations