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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    �
    -0.08
    竣工
    -0.07
    𝖚
    -0.07
     centuries
    -0.07
     тыся
    -0.07
    🏯
    -0.07
    exc
    -0.07
     MessageBoxIcon
    -0.07
    ጄ
    -0.07
    יופי
    -0.07
    POSITIVE LOGITS
     namely
    0.08
     Trap
    0.07
    .Manager
    0.07
    职业道德
    0.07
    DTV
    0.07
     smartphones
    0.07
     [&
    0.07
    Prog
    0.07
     Savage
    0.07
    idl
    0.07
    Act Density 0.003%

    No Known Activations