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

    Neuronpedia

    INDEX
    Explanations

    modelmodel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anniversary
    0.38
    刨
    0.36
     Selected
    0.36
    ීන්
    0.35
     Proposed
    0.34
    ປະກ
    0.34
     Chosen
    0.34
     Goals
    0.34
    angerschaft
    0.34
     置
    0.34
    POSITIVE LOGITS
     মডেল
    0.52
     modello
    0.51
     modelo
    0.50
     model
    0.48
    模型
    0.47
    模型的
    0.47
    ایط
    0.46
     modelos
    0.45
     मॉडल
    0.44
     моделей
    0.44
    Act Density 0.000%

    No Known Activations