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

    Neuronpedia

    INDEX
    Explanations

    swedish and danish words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     electorate
    0.36
    sourcePort
    0.34
    irds
    0.34
     moisturizing
    0.33
    ict
    0.32
     harboring
    0.32
     progesterone
    0.32
    buttonBar
    0.32
     trate
    0.32
    esia
    0.31
    POSITIVE LOGITS
     Thiel
    0.44
     Duits
    0.41
    Dens
    0.41
     Datensch
    0.40
    Dry
    0.40
    Den
    0.39
     german
    0.39
    egn
    0.39
     Denk
    0.38
     Dienste
    0.38
    Act Density 0.002%

    No Known Activations