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

    Neuronpedia

    INDEX
    Explanations

    display plot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.71
    el
    0.70
    Д
    0.68
    defin
    0.66
    at
    0.64
    $.
    0.64
    বাগ
    0.63
    ore
    0.63
    ত
    0.63
    Begin
    0.62
    POSITIVE LOGITS
    พาะ
    0.73
     congen
    0.66
     hubo
    0.66
     পালন
    0.63
     particular
    0.63
     trouve
    0.62
     mares
    0.61
     oblige
    0.61
    为空
    0.60
    嚏
    0.60
    Act Density 0.002%

    No Known Activations