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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Structure
    0.49
    хождение
    0.47
     breaks
    0.46
    ندوق
    0.46
    の本
    0.45
     countryside
    0.45
     staircase
    0.45
     პარ
    0.45
     سٹی
    0.44
     bookshelf
    0.44
    POSITIVE LOGITS
    gr
    0.59
    bold
    0.58
    ]
    0.57
    /
    0.57
    il
    0.55
    itone
    0.52
    "
    0.52
    lb
    0.52
    iper
    0.52
    s
    0.52
    Act Density 0.000%

    No Known Activations