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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ב
    1.36
    ла
    1.16
    き
    1.07
    in
    1.03
    to
    0.99
    U
    0.98
     sozial
    0.98
    la
    0.95
    ও
    0.94
    AD
    0.92
    POSITIVE LOGITS
    нном
    1.13
    ี
    1.12
    iov
    1.03
    istles
    1.02
    robes
    1.01
    yards
    1.00
    ،
    1.00
    cones
    0.99
    fontenc
    0.98
    ن
    0.97
    Act Density 0.000%

    No Known Activations