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

    Neuronpedia

    INDEX
    Explanations

    japanese lesson

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    denes
    0.46
    pharm
    0.46
    dark
    0.43
    enriched
    0.41
    her
    0.41
    ciu
    0.41
    iod
    0.40
    ase
    0.40
    on
    0.40
    herence
    0.40
    POSITIVE LOGITS
     ángulos
    0.58
     jugador
    0.56
     légende
    0.56
     játék
    0.55
     खेळा
    0.55
     diğer
    0.54
     árboles
    0.54
     amigos
    0.52
     giocatori
    0.52
     jogadores
    0.51
    Act Density 0.016%

    No Known Activations