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

    Neuronpedia

    INDEX
    Explanations

    see section or step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ánchez
    0.30
    followed
    0.29
    rijving
    0.29
    intent
    0.28
     comprises
    0.27
    这是一
    0.27
     cendré
    0.27
     conformément
    0.27
     procéder
    0.27
    These
    0.26
    POSITIVE LOGITS
     section
    0.87
     Section
    0.69
     sezione
    0.69
     sección
    0.66
    section
    0.65
     seção
    0.63
     разделе
    0.61
     раздел
    0.58
    Section
    0.57
     SECTION
    0.56
    Act Density 0.028%

    No Known Activations