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

    Neuronpedia

    INDEX
    Explanations

    introductions and affirmations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    форд
    0.46
     విధాన
    0.45
     పూర్తిగా
    0.41
     условиях
    0.41
     прозра
    0.41
     воздей
    0.40
     постоянно
    0.40
    יו
    0.40
    HAS
    0.40
    טו
    0.40
    POSITIVE LOGITS
     Yes
    0.46
     Evet
    0.44
     Liu
    0.44
     Oui
    0.42
     Jet
    0.41
     Jep
    0.41
     Kh
    0.41
     then
    0.40
     apolog
    0.39
     apologized
    0.39
    Act Density 0.008%

    No Known Activations