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

    Neuronpedia

    INDEX
    Explanations

    myths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     得
    -0.08
     kubona
    -0.08
     宝
    -0.07
     लेते
    -0.07
     escolher
    -0.07
     recib
    -0.07
     encuent
    -0.07
     combinar
    -0.07
     الله
    -0.07
     bord
    -0.07
    POSITIVE LOGITS
     misconceptions
    0.27
     misconception
    0.25
     misinformation
    0.19
     miscon
    0.18
     misunderstanding
    0.18
     misunderstand
    0.17
     misunderstood
    0.17
     misleading
    0.16
     myths
    0.15
     mistaken
    0.14
    Act Density 0.046%

    No Known Activations