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

    Neuronpedia

    INDEX
    Explanations

    code control flow and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StdHandle
    0.42
    KeepOriginal
    0.38
    ोन
    0.37
    েম
    0.37
    oretically
    0.37
     কমিউনিস্ট
    0.36
     méridionale
    0.36
     tasarım
    0.35
     ડિઝાઇન
    0.35
    selfobj
    0.35
    POSITIVE LOGITS
    0.53
     Hence
    0.43
     dari
    0.42
     který
    0.40
    ‬
    0.39
    ↵
    0.38
     sehingga
    0.38
     So
    0.38
     {
    0.38
     :)
    0.38
    Act Density 0.052%

    No Known Activations