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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    redits
    -0.79
    stery
    -0.78
    ometry
    -0.75
    Actor
    -0.75
    oiler
    -0.74
    ogram
    -0.74
    ao
    -0.73
    ounty
    -0.73
    olesterol
    -0.73
    Writer
    -0.72
    POSITIVE LOGITS
     recess
    0.72
     metab
    0.71
     exha
    0.69
     Alban
    0.66
    abb
    0.64
     habitable
    0.64
     spons
    0.64
    jriwal
    0.63
     rele
    0.62
     barg
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.