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

    Neuronpedia

    INDEX
    Explanations

    quoted or emphasized text following markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بسی
    0.63
    人々
    0.63
    мна
    0.62
    まずは
    0.61
    唠
    0.60
    这是一
    0.59
    chi
    0.58
     কেউই
    0.57
    पीरियंस
    0.57
    бры
    0.57
    POSITIVE LOGITS
     "
    1.06
     "[
    0.94
     \"
    0.86
     “
    0.84
     "__
    0.81
     "**
    0.81
     “[
    0.80
     "_
    0.80
     "'
    0.75
     "`
    0.75
    Act Density 0.088%

    No Known Activations