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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ২
    0.96
    ১
    0.88
     Five
    0.85
     다섯
    0.82
     ১
    0.80
     ۱
    0.80
     Seven
    0.80
    ৩
    0.78
     ২
    0.77
    Five
    0.75
    POSITIVE LOGITS
    Fifty
    0.72
    XXX
    0.71
    xxxxx
    0.67
    xx
    0.65
    三十
    0.64
    xxxx
    0.64
    XXXX
    0.64
    တိ
    0.64
    XX
    0.64
    onbury
    0.62
    Act Density 1.069%

    No Known Activations