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

    Neuronpedia

    INDEX
    Explanations

    gle or le endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    漓
    0.44
    itabbo
    0.42
     निपट
    0.41
    𝑳
    0.41
    rätt
    0.41
    パソコン
    0.40
    სახ
    0.39
     භාවිත
    0.38
    éfono
    0.38
    ંગી
    0.38
    POSITIVE LOGITS
    wski
    0.57
    isure
    0.54
    icester
    0.51
     le
    0.47
    ishman
    0.46
    hnung
    0.43
    ighton
    0.42
    phants
    0.42
    Le
    0.41
     레
    0.40
    Act Density 0.010%

    No Known Activations