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

    Neuronpedia

    INDEX
    Explanations

    file storage management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elenco
    0.49
    โลก
    0.46
    IBILITY
    0.44
     wszel
    0.43
     tiết
    0.42
     rougeâtres
    0.41
     Shrewsbury
    0.41
     crescente
    0.41
     blushed
    0.41
    δι
    0.40
    POSITIVE LOGITS
    फी
    0.48
    ik
    0.47
    эр
    0.47
     prudent
    0.47
    observations
    0.46
    Aging
    0.46
    蟆
    0.46
    ('
    0.46
    ༡
    0.45
    select
    0.45
    Act Density 0.000%

    No Known Activations