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

    Neuronpedia

    INDEX
    Explanations

    combining elements and aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diferença
    0.82
     milliards
    0.78
     differenza
    0.77
     diferencia
    0.76
    йга
    0.75
     notorious
    0.75
     zweimal
    0.74
     कैप्शन
    0.74
     infamous
    0.74
     млрд
    0.74
    POSITIVE LOGITS
     elements
    2.79
     aspects
    2.56
    elements
    2.42
     Elements
    2.36
    Elements
    2.26
     elementos
    2.21
     éléments
    2.19
     Aspects
    2.17
     элементы
    2.16
     Elemente
    2.03
    Act Density 0.616%

    No Known Activations