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

    Neuronpedia

    INDEX
    Explanations

    Europe and Asia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Percolation
    0.43
    虽然
    0.41
    WILL
    0.41
     advances
    0.40
    虽
    0.37
    ag
    0.37
    0.37
     হইতেই
    0.36
    gebung
    0.35
     Evening
    0.35
    POSITIVE LOGITS
     belki
    0.55
     olabilir
    0.54
     geval
    0.53
     manualmente
    0.51
     opis
    0.51
     устройства
    0.50
     pode
    0.49
     kullanıcı
    0.48
     urządzenia
    0.48
     hızlı
    0.48
    Act Density 0.006%

    No Known Activations