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

    Neuronpedia

    INDEX
    Explanations

    parts of place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DETAILS
    0.42
     NAME
    0.42
     DESCRIPTION
    0.39
     덕
    0.39
     details
    0.38
     SOURCE
    0.37
     Henn
    0.37
     Details
    0.36
     ඇති
    0.36
     darn
    0.36
    POSITIVE LOGITS
     postings
    0.49
     intéress
    0.44
     problèmes
    0.44
    operasi
    0.43
     Dou
    0.42
    Dou
    0.42
    gın
    0.41
     executar
    0.40
    腑
    0.40
    脂
    0.40
    Act Density 0.001%

    No Known Activations