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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     isomorphisms
    1.00
    tattoo
    0.95
    thirds
    0.95
     меня
    0.94
    ziak
    0.91
     permitir
    0.90
    ﺴ
    0.90
    ﻜ
    0.89
    НЫ
    0.88
     hypotheses
    0.87
    POSITIVE LOGITS
    ">
    0.68
     che
    0.66
    }
    0.66
    нки
    0.64
    其他
    0.63
     sa
    0.62
    加上
    0.62
     saga
    0.61
     oper
    0.61
     hos
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.