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

    Neuronpedia

    INDEX
    Explanations

    Underground Railroad

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    هایی
    1.60
    ესი
    1.58
    嗶
    1.58
    terbury
    1.55
    ्तीय
    1.54
    ₸
    1.52
    một
    1.51
     شماره
    1.50
    ल्लभ
    1.50
    llan
    1.49
    POSITIVE LOGITS
    И
    1.80
    '}$
    1.49
     transducers
    1.48
     unteren
    1.47
    Dream
    1.47
     сві
    1.46
    ❿
    1.45
    رحبا
    1.45
     aby
    1.42
     anvä
    1.42
    Act Density 0.000%

    No Known Activations