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

    Neuronpedia

    INDEX
    Explanations

    s followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     évolution
    0.47
     chiens
    0.47
     autres
    0.47
    دست
    0.47
    يط
    0.47
     بص
    0.46
     forças
    0.46
    ла
    0.46
     zmian
    0.46
     mě
    0.45
    POSITIVE LOGITS
    k
    0.58
    o
    0.44
    ////
    0.43
    b
    0.43
    n
    0.42
    ‍♂️
    0.42
     warehouse
    0.41
    cdot
    0.40
    uku
    0.40
    binary
    0.39
    Act Density 0.001%

    No Known Activations