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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lab
    -0.08
     crisp
    -0.07
     Crom
    -0.07
    _EPS
    -0.07
     vig
    -0.07
    iores
    -0.07
    挞
    -0.06
     البي
    -0.06
     Seamless
    -0.06
    ogeneity
    -0.06
    POSITIVE LOGITS
    ｣
    0.08
     pragma
    0.07
    rouw
    0.07
     ←
    0.07
     ли
    0.07
    огда
    0.07
     Nem
    0.07
     remote
    0.07
     Schw
    0.07
     Hou
    0.07
    Act Density 0.000%

    No Known Activations