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

    Neuronpedia

    INDEX
    Explanations

    starts with Please

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pouvons
    0.50
     milliards
    0.47
    auteur
    0.44
     możemy
    0.44
     есть
    0.44
     kita
    0.42
    ინისტრ
    0.42
     podemos
    0.41
     entusi
    0.41
     były
    0.40
    POSITIVE LOGITS
     current
    0.45
     check
    0.45
     Please
    0.43
    please
    0.43
     please
    0.43
    check
    0.41
     compare
    0.41
    HASH
    0.41
     abge
    0.40
    typ
    0.39
    Act Density 0.031%

    No Known Activations