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

    Neuronpedia

    INDEX
    Explanations

    explaining how or why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     또는
    0.23
     เรา
    0.21
     със
    0.20
    }$.
    0.20
    または
    0.20
     hoặc
    0.20
     Например
    0.20
     我們
    0.20
     Với
    0.20
     Örneğin
    0.19
    POSITIVE LOGITS
     how
    0.58
     why
    0.45
     bagaimana
    0.45
     what
    0.44
    how
    0.43
     cómo
    0.42
    如何
    0.40
     कैसे
    0.40
     hvordan
    0.39
    why
    0.37
    Act Density 0.791%

    No Known Activations