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

    Neuronpedia

    INDEX
    Explanations

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surveyed
    0.86
     complying
    0.83
     while
    0.83
     embryos
    0.81
     surveying
    0.81
     bystand
    0.80
     outside
    0.80
     which
    0.80
    鉑
    0.79
     milled
    0.78
    POSITIVE LOGITS
     файла
    0.77
     হাজার
    0.76
     évent
    0.76
    ঘ
    0.75
    يين
    0.73
    json
    0.71
    png
    0.71
    Thông
    0.70
    -,
    0.70
    古代
    0.70
    Act Density 0.053%

    No Known Activations