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

    Neuronpedia

    INDEX
    Explanations

    I need to know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ၊
    0.52
    {},
    0.47
    ₂,
    0.46
    乆
    0.42
     édition
    0.41
     নেওয়ার
    0.41
     leben
    0.40
    ™,
    0.40
    ել
    0.40
     Gerade
    0.39
    POSITIVE LOGITS
    would
    0.45
     dapat
    0.43
    could
    0.41
    Note
    0.41
    :
    0.39
     "
    0.38
     would
    0.38
    :<
    0.38
    0.38
    显得
    0.37
    Act Density 0.154%

    No Known Activations