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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     loos
    -0.07
     pony
    -0.07
     Excellence
    -0.07
    جمه
    -0.06
    boarding
    -0.06
     utrecht
    -0.06
     exempl
    -0.06
     Rams
    -0.06
    пит
    -0.06
     IPS
    -0.06
    POSITIVE LOGITS
    結構
    0.08
    固定的
    0.08
    相爱
    0.07
    ////////////////
    0.07
    (move
    0.07
     signify
    0.07
    Maria
    0.07
     Maria
    0.07
    磡
    0.07
    任何
    0.06
    Act Density 0.000%

    No Known Activations