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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rences
    -0.73
     Commissioners
    -0.68
    ocations
    -0.66
    owan
    -0.63
     intersections
    -0.63
    effic
    -0.63
     genomes
    -0.63
     allocations
    -0.62
    arcity
    -0.61
     commute
    -0.61
    POSITIVE LOGITS
    âĶģ
    0.78
    tsy
    0.73
     Mechdragon
    0.71
    ban
    0.67
    lishes
    0.66
    kees
    0.66
    ktop
    0.65
     Sorcerer
    0.65
     Syndrome
    0.65
     Outs
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.