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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    vette
    0.42
     impossible
    0.41
    rale
    0.41
     frustrated
    0.40
     menghad
    0.39
    anh
    0.39
    elijke
    0.38
    тельностью
    0.38
     işte
    0.38
    ダイヤモンド
    0.38
    POSITIVE LOGITS
     PRESS
    0.39
    ByDefault
    0.37
    加热
    0.35
    它们的
    0.35
    UTRAL
    0.35
    の間
    0.35
     warmup
    0.35
     toets
    0.35
     Pies
    0.35
     warmth
    0.34
    Act Density 0.000%

    No Known Activations