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

    Neuronpedia

    INDEX
    Explanations

    worldwide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Features
    0.40
    features
    0.39
     Polynesia
    0.39
    comments
    0.38
     Features
    0.38
    дія
    0.38
     features
    0.36
    feature
    0.36
    inFile
    0.36
    ACAO
    0.36
    POSITIVE LOGITS
     sik
    0.41
     cls
    0.38
     Howe
    0.38
     క్ష
    0.38
     আবদ্ধ
    0.37
     prez
    0.37
     disconnected
    0.36
     prototypical
    0.36
     البشر
    0.35
    ABOR
    0.35
    Act Density 0.001%

    No Known Activations