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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    in
    1.06
    പ്പോൾ
    1.00
    i
    1.00
    ی
    1.00
    walker
    0.98
    ل
    0.97
    usion
    0.95
     hozzá
    0.94
     \|
    0.93
     Lanka
    0.93
    POSITIVE LOGITS
     soprattutto
    1.36
     salido
    1.33
    ᅨ
    1.30
     oppression
    1.28
     কাউন্সিল
    1.25
    ਸੀ
    1.23
    Datos
    1.22
     impersonal
    1.22
     weit
    1.22
     posizione
    1.21
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.