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

    Neuronpedia

    INDEX
    Explanations

    Urgent/Important and Communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     операций
    0.74
    이었
    0.73
    най
    0.73
    Пу
    0.70
     иных
    0.67
     цепо
    0.66
    dropdown
    0.65
     subscripts
    0.65
    média
    0.64
     ওসি
    0.64
    POSITIVE LOGITS
    ل
    0.95
    ورت
    0.82
     Sebab
    0.82
     जहा
    0.81
     ihm
    0.80
    as
    0.78
    it
    0.77
     Entwick
    0.75
    itung
    0.75
     Ergebn
    0.74
    Act Density 0.002%

    No Known Activations