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

    Neuronpedia

    INDEX
    Explanations

    information categories and metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     शाहिद
    0.52
     Много
    0.52
    gunaan
    0.50
    லைன்
    0.49
    Ტ
    0.49
     Основ
    0.47
     Список
    0.46
    鞣
    0.46
     தவற
    0.46
    गेशन
    0.46
    POSITIVE LOGITS
     have
    0.48
    ada
    0.43
    det
    0.42
    Na
    0.42
    omi
    0.42
     calibrate
    0.42
    to
    0.42
     inhabited
    0.41
     assimilate
    0.40
     pools
    0.40
    Act Density 0.001%

    No Known Activations