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

    Neuronpedia

    INDEX
    Explanations

    code documentation comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    স্পতিবার
    0.43
    ত্যার
    0.41
    俑
    0.41
    窣
    0.39
    ྥ
    0.39
     payloads
    0.38
     কাঁদতে
    0.38
     getN
    0.38
     sasane
    0.38
     FRANCE
    0.38
    POSITIVE LOGITS
    family
    0.48
     family
    0.46
    des
    0.43
     lu
    0.43
    char
    0.43
    /
    0.40
    Ma
    0.40
     Ma
    0.39
    lar
    0.39
    big
    0.39
    Act Density 0.002%

    No Known Activations