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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    iscopal
    -0.88
    ï¸
    -0.72
     PROGRAM
    -0.71
    iton
    -0.71
    thood
    -0.69
     Forth
    -0.69
     externalToEVAOnly
    -0.69
    psons
    -0.68
    onga
    -0.66
    comings
    -0.65
    POSITIVE LOGITS
    Ob
    0.67
     repe
    0.66
    appa
    0.63
     arous
    0.62
     dispers
    0.61
    assembly
    0.58
     disperse
    0.57
     assemblies
    0.57
     assembling
    0.56
    ãĥ³ãĤ¸
    0.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.