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

    Neuronpedia

    INDEX
    Explanations

    always remember

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     futuro
    0.54
     futurs
    0.49
     devemos
    0.47
     carreg
    0.46
     futuros
    0.46
     qualquer
    0.45
     tendremos
    0.44
     futura
    0.44
     później
    0.43
     jederzeit
    0.43
    POSITIVE LOGITS
    ikti
    0.44
    tti
    0.43
     है
    0.41
    ik
    0.41
    was
    0.41
    িজ
    0.40
    FlatStyle
    0.40
    gah
    0.39
     주요
    0.39
     ▪
    0.38
    Act Density 0.002%

    No Known Activations