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

    Neuronpedia

    INDEX
    Explanations

    is your friend:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗹
    0.50
    ب
    0.48
    𝗵
    0.48
    degenerative
    0.46
    لم
    0.46
    リー
    0.45
    لز
    0.44
    柵
    0.44
    𝙜
    0.44
    기가
    0.43
    POSITIVE LOGITS
    '
    0.57
    ’
    0.54
     voert
    0.50
     Vehicle
    0.49
    at
    0.48
     vehicle
    0.45
     Bás
    0.43
     Republican
    0.42
     使用
    0.42
     didn
    0.42
    Act Density 0.002%

    No Known Activations