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

    Neuronpedia

    INDEX
    Explanations

    thousand and million

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蓦
    0.83
     याता
    0.79
    包人
    0.78
    віч
    0.78
     vedno
    0.77
    ளிர்
    0.77
    orius
    0.76
     тощо
    0.76
     எடுத்த
    0.76
     quia
    0.74
    POSITIVE LOGITS
     thousand
    1.84
     million
    1.66
    k
    1.47
    thousand
    1.46
    K
    1.39
    ,
    1.35
    million
    1.32
    ꯠ
    1.32
     Million
    1.30
     हजार
    1.23
    Act Density 0.450%

    No Known Activations