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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    drink
    1.18
    пли
    1.08
    endlich
    1.07
    nombre
    1.06
    mluv
    1.06
    redirect
    1.02
    discord
    1.01
     उपास
    1.01
    то
    1.00
    、​
    0.99
    POSITIVE LOGITS
     g
    1.04
    ویت
    1.03
     लेता
    1.02
     PV
    1.00
    NR
    0.99
    ɳ
    0.97
     AAA
    0.97
    ertet
    0.96
     G
    0.95
     RSA
    0.95
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.