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

    Neuronpedia

    INDEX
    Explanations

    numbers containing 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ich
    0.43
     Mile
    0.42
     अन्त
    0.41
    磪
    0.41
    rások
    0.41
    urally
    0.41
    chied
    0.41
    isien
    0.40
    ﯽ
    0.40
    jení
    0.40
    POSITIVE LOGITS
     semanas
    0.53
     weeks
    0.51
    weeks
    0.47
    Weeks
    0.43
     settimane
    0.41
     metodo
    0.41
     univer
    0.41
     representa
    0.40
    fer
    0.39
     domenica
    0.39
    Act Density 0.006%

    No Known Activations