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

    Neuronpedia

    INDEX
    Explanations

    digits and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    胰
    0.46
     삶
    0.44
    厦门
    0.43
    StillWater
    0.43
     রাষ্ট্র
    0.41
    খানার
    0.40
    헴
    0.40
    规模
    0.40
    AfterTax
    0.39
    职
    0.39
    POSITIVE LOGITS
     digits
    0.64
    digits
    0.55
     dígitos
    0.55
     digit
    0.54
    Digits
    0.54
     díg
    0.48
    digit
    0.47
     siete
    0.47
     Digit
    0.43
    replacement
    0.42
    Act Density 0.075%

    No Known Activations