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

    Neuronpedia

    INDEX
    Explanations

    city names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كه
    0.45
    𝚎
    0.43
    <unused653>
    0.42
     Ս
    0.42
    تهم
    0.42
    т
    0.41
    <unused2019>
    0.41
    localVarPath
    0.40
    ađ
    0.40
    )”.
    0.40
    POSITIVE LOGITS
     chicago
    0.48
    İstanbul
    0.44
    मुंबई
    0.44
     boston
    0.43
     metropolitan
    0.41
     yli
    0.40
     İstanbul
    0.40
     operasi
    0.40
     entreprise
    0.39
    上海
    0.39
    Act Density 0.274%

    No Known Activations