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

    Neuronpedia

    INDEX
    Explanations

    connecting contrasting ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    and
    0.92
    ሳሪያ
    0.81
    ByMerging
    0.75
    ຂໍ້ມ
    0.75
     montañas
    0.75
     څرنګ
    0.74
     Mã
    0.73
    𒉌
    0.73
    DD
    0.73
     moguće
    0.73
    POSITIVE LOGITS
    N
    0.98
    ↵
    0.90
    s
    0.88
     on
    0.87
    .
    0.85
    ak
    0.81
     in
    0.79
    F
    0.75
    land
    0.71
    ↵↵
    0.70
    Act Density 0.271%

    No Known Activations