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

    Neuronpedia

    INDEX
    Explanations

    syllabic sounds and prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    2.59
    एं
    2.25
    ations
    2.20
    cope
    2.19
    क्शन
    2.13
     लेकर
    2.11
    ians
    2.03
     인한
    2.02
    ATION
    1.98
    pecific
    1.98
    POSITIVE LOGITS
    ल
    3.16
    ти
    3.05
    ну
    2.67
    ב
    2.39
    ী
    2.19
    퐫
    2.17
    ہ
    2.14
    ι
    2.14
    ール
    2.03
    민국
    2.03
    Act Density 0.056%

    No Known Activations