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

    Neuronpedia

    INDEX
    Explanations

    regulations uncertainty debated width

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    7
    0.48
    ↵
    0.47
    _
    0.47
    ên
    0.46
    5
    0.45
     chemically
    0.45
    '
    0.42
    irc
    0.42
    uz
    0.42
    lz
    0.41
    POSITIVE LOGITS
     Cessna
    0.57
     영향을
    0.56
     ઓ
    0.55
    পাকিস্তানের
    0.55
    𝚄
    0.54
    新手
    0.53
    𝗧
    0.51
     Συ
    0.50
     对于
    0.50
    托管
    0.50
    Act Density 0.000%

    No Known Activations