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

    Neuronpedia

    INDEX
    Explanations

    labels and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     пато
    0.43
     with
    0.42
     afterwards
    0.41
     PMID
    0.40
     після
    0.39
     имели
    0.38
     cmds
    0.38
     சிகிச்சை
    0.38
     אחת
    0.38
     עם
    0.38
    POSITIVE LOGITS
    Jpeg
    0.46
    颀
    0.43
     Iowa
    0.43
    预测
    0.42
    Docket
    0.42
     inkjet
    0.42
    মার্ক
    0.41
    တတ်
    0.41
    द्योगिक
    0.41
    โทร
    0.41
    Act Density 0.004%

    No Known Activations