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

    Neuronpedia

    INDEX
    Explanations

    cornerstone of importance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.48
    g
    0.42
    만의
    0.41
    town
    0.41
     eventualmente
    0.40
     möglicherweise
    0.40
    society
    0.40
    t
    0.39
    title
    0.39
    q
    0.38
    POSITIVE LOGITS
    ในการ
    0.52
    ОВ
    0.52
     katika
    0.52
     în
    0.51
     causing
    0.50
     של
    0.50
     в
    0.50
     của
    0.50
     در
    0.49
     dalam
    0.48
    Act Density 0.055%

    No Known Activations