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

    Neuronpedia

    INDEX
    Explanations

    see below or next section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     presented
    0.71
     comprising
    0.69
    stva
    0.65
     tells
    0.65
    received
    0.65
    by
    0.64
     told
    0.62
    turned
    0.62
     consisting
    0.61
    Only
    0.61
    POSITIVE LOGITS
     Section
    1.39
     Appendix
    1.25
     section
    1.18
     sezione
    1.08
     subsection
    1.07
     sección
    1.05
     appendix
    1.05
     Sección
    1.05
     seção
    1.04
    Section
    1.02
    Act Density 0.025%

    No Known Activations