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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     nos
    0.53
     NOS
    0.52
    nos
    0.51
    NOS
    0.45
    Nos
    0.44
     Nos
    0.40
    adav
    0.38
    ノ
    0.37
    컹
    0.37
    পর
    0.37
    POSITIVE LOGITS
    bole
    0.48
    בו
    0.45
    boo
    0.43
    ബ്രുവരി
    0.41
    बे
    0.41
    ire
    0.40
    appendText
    0.40
    assigned
    0.40
    шире
    0.40
    бері
    0.40
    Act Density 0.000%

    No Known Activations