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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fifth
    1.18
     fifth
    1.08
    Fifth
    0.98
    fifth
    0.88
     পঞ্চম
    0.85
    第五
    0.81
     Five
    0.81
     quadruple
    0.80
     пя
    0.80
     छठे
    0.79
    POSITIVE LOGITS
    3
    2.07
     thirty
    1.97
     ٣
    1.86
    三十
    1.77
     ۳
    1.75
     ३
    1.75
     Thirty
    1.75
    thirty
    1.74
    ३
    1.72
    ۳
    1.71
    Act Density 0.869%

    No Known Activations