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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Flame
    0.43
    Rocket
    0.42
    shoulder
    0.42
    Wind
    0.41
    Flam
    0.40
     Guar
    0.39
    炎
    0.39
    dj
    0.39
     Flam
    0.39
     WM
    0.38
    POSITIVE LOGITS
     praz
    0.46
     lilies
    0.40
     upheaval
    0.40
     oblong
    0.39
     inadequacy
    0.39
     pât
    0.38
    㕕
    0.38
     pancreatic
    0.38
    ossip
    0.38
     गतिविधियों
    0.38
    Act Density 0.000%

    No Known Activations