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

    Neuronpedia

    INDEX
    Explanations

    numbers and structure markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mét
    1.01
     tổng
    0.98
     fetchData
    0.98
     обычно
    0.94
    вейца
    0.93
     Mét
    0.92
     solito
    0.92
    netic
    0.91
     ہون
    0.91
     reseñas
    0.91
    POSITIVE LOGITS
    o
    1.08
     attracted
    0.99
    بال
    0.98
    cities
    0.96
    厂
    0.95
    ক
    0.94
     cities
    0.92
    oS
    0.92
     whereby
    0.91
    elty
    0.90
    Act Density 0.000%

    No Known Activations