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

    Neuronpedia

    INDEX
    Explanations

    core values honesty

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pila
    0.61
     ईंधन
    0.59
     menina
    0.58
    square
    0.58
     ciclos
    0.58
    က်
    0.57
     तया
    0.57
    cic
    0.57
     कितने
    0.56
     squre
    0.56
    POSITIVE LOGITS
     আপাতত
    0.59
    זי
    0.58
    डील
    0.57
     penjualan
    0.56
    ወት
    0.56
    人口
    0.56
    ('/');
    0.56
    楚
    0.56
     coldest
    0.55
    নিতে
    0.55
    Act Density 0.000%

    No Known Activations