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

    Neuronpedia

    INDEX
    Explanations

    most important features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     método
    0.82
    programmed
    0.81
     workbook
    0.80
     méthode
    0.79
     cadastro
    0.77
     procedure
    0.76
    leep
    0.76
    عداد
    0.75
     metodo
    0.75
     postup
    0.75
    POSITIVE LOGITS
     importance
    0.99
    语义
    0.96
    importance
    0.96
     semantic
    0.93
     meaningful
    0.91
    Importance
    0.91
    levance
    0.86
     Importance
    0.85
     meaningfully
    0.84
     centrality
    0.82
    Act Density 1.181%

    No Known Activations