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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ל
    0.78
    vió
    0.77
     изпол
    0.77
     쓰고
    0.76
     comercial
    0.75
    ان
    0.75
     수출
    0.74
     étroit
    0.73
     essayé
    0.72
    nlü
    0.71
    POSITIVE LOGITS
    ted
    0.76
     problemy
    0.76
     "--
    0.75
     toxins
    0.71
     reactions
    0.69
     tetr
    0.69
     جمهور
    0.69
     hygiene
    0.68
     heck
    0.68
     ransom
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.