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

    Neuronpedia

    INDEX
    Explanations

    source destination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.69
     υ
    0.63
     ত
    0.63
     ஆனது
    0.61
    ’
    0.61
     costa
    0.59
     수도
    0.57
     cio
    0.57
     czego
    0.57
     operates
    0.56
    POSITIVE LOGITS
    Dollars
    0.83
     CHCl
    0.82
     солнца
    0.81
    রুখ
    0.79
     mercados
    0.77
    ͓
    0.77
     प्रोज
    0.77
     rayas
    0.77
    ဆင့်
    0.76
    iye
    0.75
    Act Density 0.004%

    No Known Activations