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

    Neuronpedia

    INDEX
    Explanations

    whenwhen youwhen i

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dàng
    1.31
    ي
    1.09
    }}^{-
    1.07
     当然
    1.04
    decade
    1.04
    ٠
    1.02
    }\|_{
    1.01
    Alter
    0.98
    து
    0.98
     mumkin
    0.97
    POSITIVE LOGITS
     faced
    2.35
     confronted
    2.33
     dealing
    2.11
     asked
    1.90
     deciding
    1.85
     discussing
    1.81
     considering
    1.79
     compared
    1.78
     viewed
    1.77
     trying
    1.71
    Act Density 0.094%

    No Known Activations