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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lyak
    -0.72
    umbn
    -0.68
    Balt
    -0.67
    snap
    -0.66
    veh
    -0.63
     Nare
    -0.63
    minimum
    -0.60
    APS
    -0.59
    Zip
    -0.58
    Child
    -0.57
    POSITIVE LOGITS
    geist
    0.60
     PU
    0.60
     Anonymous
    0.58
    entle
    0.56
     fri
    0.54
    reon
    0.53
     vein
    0.52
     burns
    0.52
     nucleus
    0.52
    oru
    0.51
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.