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

    Neuronpedia

    INDEX
    Explanations

    davinci 3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.52
     i
    0.47
     n
    0.47
     entrepreneurs
    0.45
     for
    0.44
     OH
    0.44
     ε
    0.43
     amyg
    0.43
     rug
    0.43
     I
    0.42
    POSITIVE LOGITS
    負荷
    0.52
    ㎚
    0.51
    orderLine
    0.51
    نٹ
    0.50
    ultiplier
    0.50
     بهترین
    0.50
    łac
    0.49
    allic
    0.49
    membered
    0.49
    arbit
    0.49
    Act Density 0.004%

    No Known Activations