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

    Neuronpedia

    INDEX
    Explanations

    ways of perceiving or believing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __)
    0.43
    部の
    0.42
    ্ু
    0.41
     которых
    0.40
    LEAR
    0.39
     குற
    0.39
    ਾ
    0.39
    кор
    0.38
    Hunting
    0.38
    Jump
    0.38
    POSITIVE LOGITS
     oleh
    0.72
     вами
    0.53
     by
    0.52
     всеми
    0.50
     многи
    0.48
     dearly
    0.47
     мной
    0.47
     differently
    0.46
    নীয়
    0.46
    ByUser
    0.45
    Act Density 0.028%

    No Known Activations