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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     this
    1.20
    this
    0.99
     этого
    0.86
     هذا
    0.86
     these
    0.78
     This
    0.78
     цього
    0.76
     này
    0.76
     этой
    0.73
     этом
    0.71
    POSITIVE LOGITS
     besondere
    0.61
     APIDC
    0.56
    𒂊
    0.53
    ில
    0.52
     spezielle
    0.52
    ementerian
    0.51
     бъдат
    0.50
     beserta
    0.50
     penghargaan
    0.50
    roffenen
    0.50
    Act Density 0.284%

    No Known Activations