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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     koordin
    1.05
     îi
    0.98
     evidencia
    0.97
    Não
    0.97
    Ţ
    0.97
    Tiempo
    0.95
    Jogo
    0.95
     Não
    0.94
    Kul
    0.93
    Tou
    0.93
    POSITIVE LOGITS
     mapper
    1.07
     तरह
    1.06
     اکبر
    1.06
     believer
    1.04
    swear
    1.03
     recommendation
    1.00
    략
    1.00
    涫
    1.00
     nho
    1.00
    seeker
    0.99
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.