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

    Neuronpedia

    INDEX
    Explanations

    it like it is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lib
    0.36
    の方が
    0.36
    Don
    0.34
     വേണ്ടി
    0.33
    Cord
    0.33
     것은
    0.32
     predic
    0.32
    Dt
    0.31
    그리고
    0.31
    <h2>
    0.31
    POSITIVE LOGITS
    inerary
    0.56
     rained
    0.52
     rains
    0.49
    izens
    0.48
     all
    0.45
    álie
    0.45
     allemaal
    0.43
    বনে
    0.43
     raining
    0.42
     boils
    0.41
    Act Density 0.028%

    No Known Activations