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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     floats
    -0.70
    awaru
    -0.70
     PU
    -0.68
    =-=-
    -0.68
     ANC
    -0.67
     VO
    -0.65
     Pes
    -0.64
     Vo
    -0.62
     Roose
    -0.62
     favors
    -0.61
    POSITIVE LOGITS
    thumbnails
    0.85
    PATH
    0.78
    orth
    0.77
    Benz
    0.76
    dale
    0.75
    ãĤ´
    0.74
    adh
    0.73
    âĹ¼
    0.72
    Users
    0.71
    cliffe
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.