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

    Neuronpedia

    INDEX
    Explanations

    direct comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Unisex
    0.43
     إليه
    0.42
    เสมอ
    0.40
     eran
    0.40
     годы
    0.39
     ವ್ಯ
    0.38
    ەوە
    0.38
     erau
    0.38
     nadal
    0.37
    ไม่มี
    0.37
    POSITIVE LOGITS
    pens
    0.45
     aplicação
    0.41
    Ql
    0.38
    toolStrip
    0.37
    Cet
    0.37
    плу
    0.36
    dba
    0.36
    ('|
    0.36
    experimental
    0.36
    Tou
    0.35
    Act Density 0.000%

    No Known Activations