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

    Neuronpedia

    INDEX
    Explanations

    crime and related phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ના
    1.59
    с
    1.58
    ных
    1.41
    ные
    1.40
    س
    1.38
    ра
    1.38
    де
    1.38
    ре
    1.34
     (
    1.29
    மாக
    1.28
    POSITIVE LOGITS
    ation
    1.09
    inin
    1.07
     μπορεί
    1.02
     crime
    1.02
     crappy
    1.02
     τα
    1.00
    kken
    0.99
    inya
    0.98
     допомогти
    0.96
    k
    0.96
    Act Density 0.009%

    No Known Activations