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

    Neuronpedia

    INDEX
    Explanations

    options, weights, locations, best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    О
    1.07
    К
    1.06
    г
    1.05
    бе
    1.01
    о
    1.01
    Да
    0.98
    со
    0.95
    Т
    0.93
    Д
    0.93
    Се
    0.91
    POSITIVE LOGITS
     kayaking
    0.96
     nugget
    0.94
     cortical
    0.93
     standoff
    0.88
     parietal
    0.88
     Kurdish
    0.87
     cytotoxic
    0.87
     endogenous
    0.86
     phylogeny
    0.86
     algae
    0.85
    Act Density 0.002%

    No Known Activations