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

    Neuronpedia

    INDEX
    Explanations

    quantities and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.70
    ,
    0.55
     e
    0.52
     ,
    0.52
     Blvd
    0.51
    side
    0.50
     be
    0.49
     Odyssey
    0.49
     Journal
    0.47
     Edge
    0.47
    POSITIVE LOGITS
     الأكثر
    0.59
    Benzoimidazol
    0.55
     trzec
    0.55
    IIUM
    0.55
    l
    0.55
    Geschichte
    0.54
    OLYBD
    0.54
     događ
    0.54
    ๔
    0.54
    opération
    0.53
    Act Density 0.033%

    No Known Activations