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

    Neuronpedia

    INDEX
    Explanations

    honest traders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    collation
    0.45
     Kola
    0.39
    ParallelGroup
    0.38
     Coll
    0.38
     कॉले
    0.37
     आरआर
    0.37
     collage
    0.36
    Coll
    0.36
    zość
    0.36
    Love
    0.36
    POSITIVE LOGITS
     сен
    0.42
    回来
    0.41
     команд
    0.38
     constants
    0.38
     постоян
    0.37
     permeates
    0.37
    constants
    0.37
    回來
    0.37
     ACS
    0.36
     permeate
    0.36
    Act Density 0.000%

    No Known Activations