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

    Neuronpedia

    INDEX
    Explanations

    reporting information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     evolving
    1.03
     where
    1.03
     providing
    0.97
     gdzie
    0.93
     serving
    0.93
     always
    0.92
     얘는
    0.90
     conferring
    0.89
     prů
    0.89
     funcionando
    0.88
    POSITIVE LOGITS
     reportedly
    1.25
    Apparently
    1.08
     Apparently
    1.04
     allegedly
    1.04
     намере
    1.01
     amid
    1.00
    apparently
    1.00
     જણાવ્યું
    0.99
     believes
    0.95
    citing
    0.94
    Act Density 0.027%

    No Known Activations