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

    Neuronpedia

    INDEX
    Explanations

    más comparative adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     매우
    0.70
    Very
    0.66
     Extremely
    0.66
     очень
    0.65
     досить
    0.65
     Very
    0.64
     весьма
    0.62
     extremely
    0.61
     vrlo
    0.61
     انتہائی
    0.61
    POSITIVE LOGITS
     grande
    0.68
     rápido
    0.64
     potente
    0.61
     temprano
    0.61
    多的
    0.60
     fácil
    0.59
     tarde
    0.59
     fuerte
    0.59
     allá
    0.59
     parecido
    0.57
    Act Density 0.020%

    No Known Activations