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

    Neuronpedia

    INDEX
    Explanations

    programming syntax or database queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     июня
    0.89
     کرنے
    0.80
    मील
    0.79
    ὖ
    0.79
    ὗ
    0.79
     кеңсеси
    0.78
    торое
    0.77
    เอียด
    0.77
     Watercolour
    0.77
     বর্ণের
    0.77
    POSITIVE LOGITS
     don
    0.77
      
    0.72
     env
    0.70
     derr
    0.66
     qr
    0.66
    0.65
    ચ્છ
    0.64
       
    0.64
     la
    0.63
     smartphone
    0.63
    Act Density 0.001%

    No Known Activations