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

    Neuronpedia

    INDEX
    Explanations

    been + verb/-ing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    1.56
    y
    1.27
    dU
    1.17
    ﺑ
    1.11
     dhamm
    1.09
     ответы
    1.09
    c
    1.07
    t
    1.06
    dı
    0.99
    dX
    0.99
    POSITIVE LOGITS
    م
    1.76
    在
    1.45
    ن
    1.44
    ন
    1.41
    न
    1.36
    र
    1.33
    ر
    1.30
    no
    1.27
    ation
    1.25
    ますが
    1.20
    Act Density 0.028%

    No Known Activations