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

    Neuronpedia

    INDEX
    Explanations

    features, advancements, status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Proced
    0.45
    𝑋
    0.42
     fontstyle
    0.41
     Eras
    0.40
     کیے
    0.40
     ار
    0.40
     Conting
    0.40
     Nave
    0.39
     Uda
    0.39
    fromDate
    0.39
    POSITIVE LOGITS
     WORTH
    0.44
     thrift
    0.43
    ોર્ટ
    0.43
    net
    0.41
    いい
    0.41
     whatnot
    0.41
    今日も
    0.41
    にある
    0.40
     कोटी
    0.40
    ит
    0.39
    Act Density 0.015%

    No Known Activations