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

    Neuronpedia

    INDEX
    Explanations

    numbers and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Swim
    0.41
    Doe
    0.40
    PC
    0.38
    мина
    0.38
     PC
    0.37
    Af
    0.37
     presented
    0.37
    ipl
    0.35
    moc
    0.35
    En
    0.35
    POSITIVE LOGITS
     देम
    0.46
     ہوئے۔
    0.43
     sixteenth
    0.41
    सेप्शन
    0.40
    क्षत्र
    0.37
    adiyah
    0.37
    cud
    0.36
     infant
    0.36
    úrese
    0.36
    ণা
    0.36
    Act Density 0.011%

    No Known Activations