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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.86
    glomer
    -0.86
    én
    -0.85
    ensor
    -0.80
    FORE
    -0.75
     plur
    -0.75
    iple
    -0.74
    é¾į
    -0.71
    enser
    -0.69
    ciplinary
    -0.69
    POSITIVE LOGITS
    wagen
    0.65
    tes
    0.61
     Coff
    0.61
     messages
    0.61
     philosophy
    0.61
     messaging
    0.60
    auga
    0.58
    Sham
    0.58
     Medicare
    0.57
    \-
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.