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

    Neuronpedia

    INDEX
    Explanations

    listing specific item names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    если
    0.47
     метод
    0.46
    lors
    0.46
    ко
    0.46
    кон
    0.45
    к
    0.45
    ור
    0.44
    дың
    0.43
     кон
    0.43
     большого
    0.43
    POSITIVE LOGITS
     northern
    0.47
     dyr
    0.46
     utc
    0.46
     bronze
    0.44
     lipids
    0.44
    ♯
    0.43
     perawatan
    0.43
     vintage
    0.42
     appearing
    0.42
     estrogen
    0.41
    Act Density 0.003%

    No Known Activations