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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     gráf
    0.53
    Initially
    0.50
     interag
    0.50
    葳
    0.49
    вано
    0.49
    你
    0.49
    ,
    0.49
     Inicial
    0.48
    岗
    0.46
     você
    0.46
    POSITIVE LOGITS
    ystem
    0.53
     किसान
    0.50
    particle
    0.50
    lead
    0.50
    ඩ්
    0.49
    mathscr
    0.49
    irus
    0.48
    hint
    0.48
    jet
    0.48
    toothbrush
    0.48
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.