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

    Neuronpedia

    INDEX
    Explanations

    "and" keyword

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    攽
    0.38
    __)
    0.37
    :')
    0.37
     desto
    0.37
    ²)
    0.36
    tand
    0.36
     البي
    0.35
     scheint
    0.35
    ગાહી
    0.35
    น่า
    0.35
    POSITIVE LOGITS
     Анд
    0.50
     andro
    0.49
     Andi
    0.47
    romeda
    0.46
     Andreev
    0.46
    rzej
    0.46
    ersen
    0.45
    ंगाबाद
    0.44
    ியும்
    0.44
    ROID
    0.44
    Act Density 0.012%

    No Known Activations