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

    Neuronpedia

    INDEX
    Explanations

    quantifying proportions or portions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мещение
    0.42
    esc
    0.39
    Low
    0.39
    سات
    0.39
    anos
    0.38
     ninety
    0.38
    bard
    0.38
    apest
    0.37
    stant
    0.37
    anh
    0.36
    POSITIVE LOGITS
     proportion
    1.29
    proportion
    1.12
     proporción
    1.09
     portion
    1.07
     Proportion
    1.02
    比例
    0.99
     proportions
    0.98
    portion
    0.97
     pourcentage
    0.95
     fraction
    0.95
    Act Density 0.016%

    No Known Activations