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

    Neuronpedia

    INDEX
    Explanations

    the same way humans do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    相应
    0.76
    ificaciones
    0.76
     thậm
    0.75
    ខ្សែ
    0.75
     bzw
    0.75
    甚至
    0.75
     coupes
    0.75
    IFICATIONS
    0.74
    cies
    0.73
    相应的
    0.73
    POSITIVE LOGITS
     same
    0.98
     Same
    0.80
    Same
    0.76
     traditional
    0.75
     mismo
    0.75
    same
    0.72
     tradisional
    0.72
     misma
    0.71
     earthy
    0.69
    Traditional
    0.68
    Act Density 0.037%

    No Known Activations