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

    Neuronpedia

    INDEX
    Explanations

    Okay, comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overwhelmingly
    0.66
     initiate
    0.64
     Initiate
    0.61
    溢
    0.60
     задума
    0.59
     यूनिवर्स
    0.57
     dedica
    0.57
     जितना
    0.57
     asks
    0.56
     питань
    0.56
    POSITIVE LOGITS
    :");
    0.78
    Results
    0.76
     radial
    0.75
    Result
    0.74
    stri
    0.74
     seseorang
    0.74
    的效果
    0.73
     contractions
    0.73
     gend
    0.73
    टाम
    0.73
    Act Density 0.072%

    No Known Activations