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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rootScope
    0.94
    e
    0.80
    ح
    0.79
    शुदा
    0.79
    ções
    0.79
    el
    0.77
    itations
    0.76
     rejo
    0.75
    ның
    0.74
    𝘁
    0.73
    POSITIVE LOGITS
    Neither
    1.00
     Neither
    0.95
    Де
    0.90
    િક
    0.88
    磪
    0.87
    𝘿
    0.84
    𝙋
    0.83
    一来
    0.83
    ⚤
    0.81
     etiqu
    0.80
    Act Density 0.004%

    No Known Activations