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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jess
    0.48
    анали
    0.43
    łoż
    0.42
     सैक
    0.41
    ീ
    0.41
     Анали
    0.41
    äischen
    0.40
     hess
    0.40
     Quỳnh
    0.39
    σκευ
    0.39
    POSITIVE LOGITS
    ール
    0.43
    ].”
    0.40
    ...”
    0.40
    ”，
    0.39
     सहमत
    0.39
     কে
    0.39
     commemorating
    0.39
    を受け
    0.38
    ‌ನ
    0.37
     ಅನ್ನು
    0.36
    Act Density 0.001%

    No Known Activations