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

    Neuronpedia

    INDEX
    Explanations

    Describes Dutch and German

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ติ
    0.60
     sub
    0.58
    enin
    0.55
     спи
    0.55
    uly
    0.54
     기
    0.54
    stalk
    0.54
    trat
    0.53
    inity
    0.53
    νας
    0.53
    POSITIVE LOGITS
    ä
    0.89
    attend
    0.86
     rendel
    0.82
    æ
    0.81
    ogens
    0.81
    ällt
    0.80
    otene
    0.79
    ogène
    0.78
    issense
    0.77
    ogen
    0.77
    Act Density 0.026%

    No Known Activations