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

    Neuronpedia

    INDEX
    Explanations

    terminal navigation commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を受ける
    0.40
    udos
    0.38
    টিও
    0.36
     ríos
    0.35
    ವೆ
    0.35
     vale
    0.35
     ?”
    0.35
    ؤں
    0.34
    APOLIS
    0.34
     получится
    0.34
    POSITIVE LOGITS
    cd
    0.58
     navigate
    0.55
     Navigate
    0.52
     enter
    0.51
    navigate
    0.50
    Navigate
    0.49
     cd
    0.47
     cds
    0.45
    Cd
    0.44
     navigated
    0.44
    Act Density 0.002%

    No Known Activations