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

    Neuronpedia

    INDEX
    Explanations

    simple, structured, or tiered approaches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     この
    0.57
     değer
    0.57
     そして
    0.56
     certifies
    0.56
     your
    0.55
     bezpiecze
    0.55
    Your
    0.55
    Resultado
    0.54
     sentimento
    0.54
    Tha
    0.54
    POSITIVE LOGITS
     simple
    0.94
     menggunakan
    0.91
     flexible
    0.89
     pliable
    0.89
     structured
    0.87
    简单的
    0.86
     tiered
    0.86
     spreadsheets
    0.85
     modular
    0.84
     jednoduch
    0.84
    Act Density 0.008%

    No Known Activations