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

    Neuronpedia

    INDEX
    Explanations

    creating or used as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Squared
    0.43
     condensed
    0.42
     sprinkled
    0.41
     sprinkles
    0.41
    marker
    0.40
    的三
    0.40
     deviates
    0.39
     condensation
    0.39
     মর্টার
    0.39
     boroughs
    0.39
    POSITIVE LOGITS
    బో
    0.45
     описание
    0.45
     জুটি
    0.45
     जास्त
    0.44
    әм
    0.43
     खूप
    0.43
    ITERATURE
    0.43
    𝔦
    0.43
     juara
    0.42
     ingin
    0.42
    Act Density 0.003%

    No Known Activations