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

    Neuronpedia

    INDEX
    Explanations

    world-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अभिनंदन
    1.04
    கள்
    1.00
    ।*
    0.98
    வும்
    0.98
    粘贴
    0.98
     तंत्र
    0.97
    кость
    0.97
    的版本
    0.97
    columnIndex
    0.96
    README
    0.96
    POSITIVE LOGITS
     measure
    0.99
     czasem
    0.80
     Measure
    0.80
     chur
    0.80
    un
    0.79
    ü
    0.77
     ø
    0.77
    ح
    0.76
     invo
    0.76
    le
    0.74
    Act Density 0.000%

    No Known Activations