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

    Neuronpedia

    INDEX
    Explanations

    CN and variations (CNH, CNBC, CNOT)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    贲
    0.40
     erweit
    0.40
     თვით
    0.39
    苾
    0.39
     Saur
    0.38
    ूटूथ
    0.38
    鹑
    0.38
    夔
    0.38
    ֜
    0.38
    setWidth
    0.37
    POSITIVE LOGITS
     CN
    0.54
    ni
    0.52
    CN
    0.52
    Cin
    0.48
    cn
    0.47
     cin
    0.47
    ratulations
    0.46
     CIN
    0.46
     CNT
    0.45
     CNN
    0.45
    Act Density 0.007%

    No Known Activations