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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Actors
    0.41
    κρι
    0.41
    اس
    0.41
    Scient
    0.40
    Hostname
    0.40
    டியே
    0.39
    स
    0.39
     कहता
    0.39
    சிக்கும்
    0.39
     बगैर
    0.39
    POSITIVE LOGITS
     shorten
    0.43
     bowtie
    0.42
     bearish
    0.41
     dissatisf
    0.39
     전류
    0.39
    igde
    0.38
       
    0.38
     minify
    0.38
     unfavorable
    0.38
     polycrystalline
    0.38
    Act Density 0.011%

    No Known Activations