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

    Neuronpedia

    INDEX
    Explanations

    avocado

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     averaging
    0.42
    splitting
    0.42
     avatars
    0.41
    諾
    0.41
     నో
    0.40
     μαγγ
    0.40
     χρη
    0.39
     валю
    0.39
    Vas
    0.38
    asaan
    0.38
    POSITIVE LOGITS
    ok
    0.50
    ocado
    0.48
    cad
    0.45
    కా
    0.44
    ок
    0.43
    acate
    0.42
     Cá
    0.41
    acola
    0.41
    وك
    0.40
    ruga
    0.40
    Act Density 0.001%

    No Known Activations