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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ヨーク
    0.50
    ىل
    0.48
    초
    0.45
     theses
    0.45
    lex
    0.44
    Ky
    0.44
    Final
    0.44
    Biology
    0.43
    Sum
    0.42
     Allocate
    0.42
    POSITIVE LOGITS
    ਿ
    0.55
     карти
    0.49
     impunity
    0.47
     cephal
    0.46
    ة
    0.46
    ר
    0.46
     छोटे
    0.46
     casi
    0.45
    ิ
    0.45
     interstate
    0.44
    Act Density 0.001%

    No Known Activations