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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     конкурен
    0.42
     будь
    0.42
     дра
    0.41
     монта
    0.41
     бед
    0.41
     компетен
    0.41
    дра
    0.41
     доступа
    0.41
    ComponentName
    0.41
     συγκεκρι
    0.41
    POSITIVE LOGITS
    대
    0.45
    乳
    0.43
    粌
    0.42
    蜕
    0.41
     isolation
    0.40
     sustaining
    0.39
     iso
    0.39
    𝒎
    0.39
    polarized
    0.38
     air
    0.38
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.