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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    出来的
    0.42
     There
    0.41
     గ
    0.41
     Number
    0.41
    のが
    0.41
     Straight
    0.40
     Numbers
    0.40
     Constitution
    0.40
     Whole
    0.39
     From
    0.39
    POSITIVE LOGITS
    ড়যন্ত্র
    0.51
     rhizosphere
    0.47
     weakens
    0.44
    alaya
    0.43
    véd
    0.42
     utilisent
    0.42
     broni
    0.42
     включают
    0.42
    कृष्ण
    0.41
     αδ
    0.41
    Act Density 0.001%

    No Known Activations