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

    Neuronpedia

    INDEX
    Explanations

    lists separated by commas and 'and'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    1.61
     adsor
    1.26
     одежды
    1.25
    ﺝ
    1.25
     다른
    1.21
    erdale
    1.19
    entimes
    1.18
    शेखर
    1.17
    торое
    1.17
     benda
    1.16
    POSITIVE LOGITS
     НА
    1.09
    Más
    1.05
    Für
    1.04
    Así
    0.99
     Сьогодні
    0.99
    ATIV
    0.95
    Η
    0.95
    Nella
    0.93
    РА
    0.93
    ENT
    0.91
    Act Density 0.266%

    No Known Activations