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

    Neuronpedia

    INDEX
    Explanations

    hello followed by content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pareto
    0.33
     deg
    0.33
     cuticle
    0.32
     suscept
    0.31
     عدد
    0.31
     physicochemical
    0.31
     tekst
    0.31
     voidaan
    0.31
     mitotic
    0.30
     kinet
    0.30
    POSITIVE LOGITS
    楼主
    0.34
     başladı
    0.33
     usuario
    0.33
    atorio
    0.31
     anunciou
    0.31
     ciudadanos
    0.30
    閣
    0.30
     anunció
    0.30
    ão
    0.30
    POSAL
    0.30
    Act Density 0.062%

    No Known Activations