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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    mount
    -0.80
    forts
    -0.73
    Äĩ
    -0.69
    Kings
    -0.68
     Glac
    -0.65
    burgh
    -0.65
    gage
    -0.65
    olesc
    -0.63
     Consumer
    -0.62
    gob
    -0.62
    POSITIVE LOGITS
    hari
    0.76
    ariat
    0.74
     Nguyen
    0.67
    iary
    0.65
    ukong
    0.65
    RM
    0.65
    URA
    0.61
     UM
    0.61
     uncovered
    0.60
    OME
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.