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

    Neuronpedia

    INDEX
    Explanations

    autoencoders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ва
    0.71
    रा
    0.63
    انى
    0.59
    டைய
    0.59
     identities
    0.57
    بان
    0.55
    사
    0.54
     awaited
    0.54
    던
    0.54
    其他
    0.54
    POSITIVE LOGITS
    odymium
    0.61
     glm
    0.61
    in
    0.57
     فهي
    0.57
    NSString
    0.56
    şti
    0.56
     Tensorflow
    0.56
     אם
    0.56
    神经网络
    0.55
     fgets
    0.55
    Act Density 0.007%

    No Known Activations