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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    作為
    0.47
    PROGRAM
    0.45
    mathcal
    0.43
     fisc
    0.43
     gmin
    0.43
     empresa
    0.42
    onClick
    0.42
    Revel
    0.42
    ○
    0.42
    /)
    0.41
    POSITIVE LOGITS
     dumbbells
    0.53
     endearing
    0.53
     unwittingly
    0.51
     galloping
    0.50
     invading
    0.50
     electrically
    0.48
     ionized
    0.46
     pajama
    0.46
     unmistakable
    0.45
     exudes
    0.45
    Act Density 0.014%

    No Known Activations