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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ഗ്ര
    1.20
    <unused438>
    1.19
     Matters
    1.18
    恜
    1.16
    <unused2176>
    1.12
    Ⅺ
    1.12
    <unused711>
    1.11
     Weapons
    1.11
     중요한
    1.10
    <unused433>
    1.10
    POSITIVE LOGITS
     (
    0.95
     costo
    0.86
     risque
    0.84
     risk
    0.82
     custo
    0.80
     rischio
    0.78
    ris
    0.78
     прид
    0.78
     +
    0.77
     hơi
    0.77
    Act Density 0.599%

    No Known Activations