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

    Neuronpedia

    INDEX
    Explanations

    places, concepts, and tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    0.57
    fehler
    0.56
    šení
    0.55
    ви
    0.53
    toadd
    0.52
    вик
    0.50
    to
    0.50
    пу
    0.49
    нец
    0.48
    техни
    0.48
    POSITIVE LOGITS
    Anh
    0.53
    ມັນ
    0.51
    .
    0.49
     homegrown
    0.48
    Ketika
    0.46
     ஆண்டுக
    0.45
     chữ
    0.45
    学历
    0.44
     remnants
    0.43
    Mem
    0.43
    Act Density 0.000%

    No Known Activations