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

    Neuronpedia

    INDEX
    Explanations

    your [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ings
    0.74
     arrivals
    0.73
    ாம
    0.73
     touchdowns
    0.73
     bungalows
    0.73
    ations
    0.72
     দায়িত্ব
    0.71
     ।
    0.71
     что
    0.71
     digraph
    0.71
    POSITIVE LOGITS
    देशीर
    0.64
    isEqualTo
    0.61
    ージー
    0.61
    synt
    0.60
     pudi
    0.60
    wają
    0.59
    gna
    0.58
     penulis
    0.57
    ত্রী
    0.56
    样子
    0.56
    Act Density 0.052%

    No Known Activations