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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     conferred
    1.02
    કા
    1.01
    لاك
    1.00
    ません
    0.99
    ழ்
    0.95
    タウン
    0.94
    勹
    0.93
    под
    0.93
    并将
    0.93
    হা
    0.92
    POSITIVE LOGITS
    ประกอบ
    1.09
    樍
    1.03
     scor
    1.00
    ted
    0.99
     infusion
    0.97
    Ⴝ
    0.97
     pastas
    0.96
     combinação
    0.95
     razvoj
    0.95
    isasi
    0.94
    Act Density 0.000%

    No Known Activations