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

    Neuronpedia

    INDEX
    Explanations

    list indexing and sorting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     اب
    0.26
    Loksatta
    0.25
     شب
    0.24
     وتش
    0.24
     القيام
    0.24
    rául
    0.24
     ખે
    0.24
    GUNDABAD
    0.24
     تا
    0.24
     فو
    0.23
    POSITIVE LOGITS
    s
    0.29
     values
    0.26
     other
    0.25
     left
    0.25
    N
    0.25
     padding
    0.25
     be
    0.25
    ity
    0.24
     while
    0.24
    0
    0.24
    Act Density 5.960%

    No Known Activations