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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     gegeben
    1.13
    in
    1.06
    apor
    1.04
     zv
    1.04
     $€
    1.01
    ف
    1.00
     günstig
    0.99
     $\$
    0.99
     muut
    0.97
    দানি
    0.97
    POSITIVE LOGITS
    욱
    1.45
     trapped
    1.22
     Игра
    1.21
    ventud
    1.19
     BuildableName
    1.19
    entreprise
    1.15
    usuario
    1.14
     apoi
    1.13
     буд
    1.13
     乳
    1.12
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.