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

    Neuronpedia

    INDEX
    Explanations

    the [capitalized word]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dotycz
    1.07
    લમાં
    1.02
    ル
    1.01
    on
    1.00
    ról
    0.99
     deuxième
    0.98
     restaurants
    0.95
    t
    0.95
    ib
    0.94
    yers
    0.93
    POSITIVE LOGITS
    \
    1.01
    하여
    0.99
    ؘ
    0.94
    ㅤ
    0.93
     પસ
    0.93
    ם
    0.93
    '
    0.92
    ने
    0.91
    )$
    0.90
    と考え
    0.89
    Act Density 0.004%

    No Known Activations