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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    haar
    -0.80
     srf
    -0.67
     mathemat
    -0.66
     compr
    -0.66
    jri
    -0.65
    lamm
    -0.65
     relat
    -0.64
    ipel
    -0.63
     looting
    -0.63
     describ
    -0.63
    POSITIVE LOGITS
    Office
    0.85
    bird
    0.78
    services
    0.76
    ridges
    0.73
    ieu
    0.70
    office
    0.69
    mate
    0.67
    inder
    0.67
    doors
    0.66
    eon
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.