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

    Neuronpedia

    INDEX
    Explanations

    Vietnamese greetings and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    っと
    0.95
    ﺏ
    0.90
    ﺙ
    0.89
     poodle
    0.87
     predictable
    0.86
    ারন
    0.85
     valet
    0.85
     revel
    0.84
     interdependent
    0.83
     roster
    0.83
    POSITIVE LOGITS
    צ
    0.79
     угле
    0.78
    MORDOR
    0.78
    }}^{
    0.77
    ں
    0.77
    го
    0.77
    Competing
    0.77
     ugljik
    0.76
     ۾
    0.75
    нем
    0.75
    Act Density 0.000%

    No Known Activations