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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    🍜
    0.57
     collectives
    0.53
     punctatis
    0.53
     doctrinal
    0.52
     आरक्षण
    0.52
     bhavanti
    0.52
     vattati
    0.51
     cognitiva
    0.51
    ıları
    0.50
     divergents
    0.50
    POSITIVE LOGITS
    t
    0.64
    in
    0.59
    n
    0.57
    기
    0.54
    元
    0.51
    Version
    0.50
    Custom
    0.50
     B
    0.50
    l
    0.50
    Style
    0.49
    Act Density 0.002%

    No Known Activations