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

    Neuronpedia

    INDEX
    Explanations

    thirty and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    第五
    0.49
     quinto
    0.48
     fifth
    0.45
    fifth
    0.44
    Fifth
    0.43
    <unused84>
    0.42
     cinquième
    0.42
    fourth
    0.41
    seventh
    0.41
     пя
    0.40
    POSITIVE LOGITS
    3
    2.09
     thirty
    1.90
     ३
    1.90
     Thirty
    1.84
     ۳
    1.84
    ３
    1.77
     ૩
    1.76
    ३
    1.69
     ٣
    1.66
    ۳
    1.66
    Act Density 0.520%

    No Known Activations