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

    Neuronpedia

    INDEX
    Explanations

    Italian names, places, food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uns
    0.63
     adapt
    0.62
     Tanger
    0.62
    থ
    0.58
     internal
    0.58
     Yes
    0.58
     /*
    0.56
     intros
    0.56
    ढ़
    0.55
     Euclidean
    0.55
    POSITIVE LOGITS
     italiani
    1.36
     italiano
    1.31
    elli
    1.30
    acci
    1.29
    accio
    1.27
    igli
    1.24
    azzo
    1.23
    etti
    1.23
    letti
    1.22
    ellini
    1.22
    Act Density 0.055%

    No Known Activations