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

    Neuronpedia

    INDEX
    Explanations

    Okay, what's this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     downright
    1.00
     наиболее
    0.93
     pretty
    0.92
     aquellas
    0.89
     تلك
    0.89
     oldukça
    0.89
     particularmente
    0.88
     quite
    0.87
     найбільш
    0.85
     znacznie
    0.85
    POSITIVE LOGITS
    –
    1.16
    —
    1.11
     $-$
    1.06
     —
    1.02
     -
    1.01
     –
    1.00
    ––
    0.97
     −
    0.91
    --
    0.88
    -$\
    0.85
    Act Density 0.019%

    No Known Activations