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

    Neuronpedia

    INDEX
    Explanations

    igualdad, matemáticas, física

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hoodies
    0.52
     hegemony
    0.52
     omnichannel
    0.52
    ากหลาย
    0.52
     humanist
    0.51
     idioms
    0.51
     drummer
    0.50
     conspiracy
    0.49
     ඔවුන්
    0.49
     mercenaries
    0.49
    POSITIVE LOGITS
     igual
    0.79
     polinomio
    0.67
    igual
    0.65
     mediante
    0.62
     seno
    0.62
     raíz
    0.61
     encontramos
    0.59
     coseno
    0.59
     iguales
    0.59
     despe
    0.59
    Act Density 0.037%

    No Known Activations