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

    Neuronpedia

    INDEX
    Explanations

    us or you phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </em>
    -2.06
    \
    -2.06
     buscando
    -1.89
    pantalones
    -1.79
     самы
    -1.79
     tomando
    -1.75
    但她
    -1.72
     is
    -1.66
     znaleźć
    -1.66
    但他
    -1.60
    POSITIVE LOGITS
     a
    1.91
     være
    1.79
    来歴
    1.71
     {
    1.70
     jsme
    1.63
     användas
    1.60
     berharap
    1.60
     咲
    1.59
    ){$
    1.57
    anwalt
    1.55
    Act Density 0.006%

    No Known Activations