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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rils
    -0.95
    pex
    -0.83
    aline
    -0.80
    rams
    -0.79
    daq
    -0.70
    umi
    -0.69
    rin
    -0.67
    riel
    -0.67
     oxide
    -0.66
    REF
    -0.65
    POSITIVE LOGITS
     Austral
    0.80
     Maj
    0.70
    plex
    0.69
     Conserv
    0.65
     honor
    0.62
     Gent
    0.62
    Austral
    0.61
     Brach
    0.60
    bid
    0.59
     Curve
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.