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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     shreds
    0.58
     feats
    0.50
    пление
    0.50
     inclusions
    0.45
     ruins
    0.45
     Outstanding
    0.44
     shackles
    0.44
     apical
    0.44
     processed
    0.44
     disqual
    0.44
    POSITIVE LOGITS
    ουν
    0.57
    corporate
    0.49
    颜
    0.49
    arm
    0.48
    Victory
    0.46
    喿
    0.46
    Clark
    0.45
    Fors
    0.45
    ad
    0.45
    është
    0.45
    Act Density 0.000%

    No Known Activations