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

    Neuronpedia

    INDEX
    Explanations

    is a good/perfect/ideal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bueno
    0.46
     desirable
    0.43
     संबंधी
    0.41
     дело
    0.41
    好
    0.41
     necessário
    0.41
     necessario
    0.40
     erforderlich
    0.39
     好
    0.38
     needn
    0.38
    POSITIVE LOGITS
     prime
    0.43
     جایی
    0.42
     perfecta
    0.41
     PERFECT
    0.40
     perfeita
    0.40
     ideale
    0.39
     perfekte
    0.39
     PRIME
    0.39
    Scope
    0.37
     parfaite
    0.37
    Act Density 0.013%

    No Known Activations