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

    Neuronpedia

    INDEX
    Explanations

    year 2023 standings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jahrze
    0.43
    стива
    0.41
    તાવ
    0.41
    ଥି
    0.39
    Phillips
    0.39
    >?
    0.39
    рьох
    0.39
     स्किप
    0.39
     שנים
    0.38
    την
    0.38
    POSITIVE LOGITS
     lately
    0.55
     undefeated
    0.54
     bisher
    0.49
     unbeaten
    0.45
     Allgemeine
    0.43
     bislang
    0.42
     agora
    0.42
     ماہ
    0.41
     இருக்கிறார்
    0.41
     ప్రస్తుతం
    0.41
    Act Density 0.073%

    No Known Activations