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

    Neuronpedia

    INDEX
    Explanations

    initiates actions or processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mieć
    0.38
     imati
    0.37
     использоваться
    0.31
     være
    0.30
     habían
    0.30
     essere
    0.30
     иметь
    0.30
     être
    0.30
     ہونا
    0.29
     کہنا
    0.29
    POSITIVE LOGITS
     chooses
    0.52
     gets
    0.51
     alır
    0.50
     prepares
    0.49
     decides
    0.49
     creates
    0.49
     manages
    0.48
     adjusts
    0.48
     engages
    0.47
     learns
    0.46
    Act Density 0.214%

    No Known Activations